Paper Digest: Recent Papers on Semantic Segmentation
Paper Digest Team extracted all recent Semantic Segmentation related papers on our radar, and generated highlight sentences for them. The results are then sorted by relevance & date. In addition to this ‘static’ page, we also provide a real-time version of this article, which has more coverage and is updated in real time to include the most recent updates on this topic.
If you do not want to miss any interesting academic paper, you are welcome to sign up our free daily paper digest service to get updates on new papers published in your area every day. You are also welcome to follow us on Twitter and Linkedin to get updated with new conference digests.
Paper Digest Team
team@paperdigest.org
TABLE 1: Paper Digest: Recent Papers on Semantic Segmentation
| Paper | Author(s) | Source | Date | |
|---|---|---|---|---|
| 1 | MDA-Net: Multi-Dimensional Attention-Based Neural Network for 3D Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this challenge, we propose a multi-dimensional attention network (MDA-Net) to efficiently integrate slice-wise, spatial, and channel-wise attention into a U-Net based network, which results in high segmentation accuracy with a low computational cost. |
Rutu Gandhi; Yi Hong; | arxiv-cs.CV | 2021-05-10 |
| 2 | An Attention-Fused Network for Semantic Segmentation of Very-High-Resolution Remote Sensing Imagery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a multipath encoder structure to extract features of multipath inputs, a multipath attention-fused block module to fuse multipath features, and a refinement attention-fused block module to fuse high-level abstract features and low-level spatial features. |
XUAN YANG et. al. | arxiv-cs.CV | 2021-05-10 |
| 3 | Deep Feature Selection-and-fusion for RGB-D Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes a unified and efficient feature selectionand-fusion network (FSFNet), which contains a symmetric cross-modality residual fusion module used for explicit fusion of multi-modality information. |
Yuejiao Su; Yuan Yuan; Zhiyu Jiang; | arxiv-cs.CV | 2021-05-10 |
| 4 | PillarSegNet: Pillar-based Semantic Grid Map Estimation Using Sparse LiDAR Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To train and evaluate our approach, we use both sparse and dense ground truth, where the dense ground truth is obtained from multiple superimposed scans. |
Juncong Fei; Kunyu Peng; Philipp Heidenreich; Frank Bieder; Christoph Stiller; | arxiv-cs.CV | 2021-05-10 |
| 5 | Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a Paired Rain Removal Network (PRRNet), which exploits both stereo images and semantic information. |
KAIHAO ZHANG et. al. | arxiv-cs.CV | 2021-05-09 |
| 6 | Seismic Fault Segmentation Via 3D-CNN Training By A Few 2D Slices Labels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we present a new binary cross-entropy and smooth L1 loss ({\lambda}-BCE and {\lambda}-smooth L1) to effectively train 3D-CNN by sampling some 2D slices from 3D seismic data, so that the model can learn the segmentation of 3D seismic data from a few 2D slices. |
YiMin Dou; Kewen Li; Jianbing Zhu; Xiao Li; Yingjie Xi; | arxiv-cs.CV | 2021-05-09 |
| 7 | CFPNet-M: A Light-Weight Encoder-Decoder Based Network for Multimodal Biomedical Image Real-Time Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on these two modifications, we proposed a novel light-weight architecture — Channel-wise Feature Pyramid Network for Medicine (CFPNet-M). |
Ange Lou; Shuyue Guan; Murray Loew; | arxiv-cs.CV | 2021-05-09 |
| 8 | Video Class Agnostic Segmentation with Contrastive Learningfor Autonomous Driving Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel auxiliary contrastive loss to learn the segmentation of known classes and unknown objects. We further release a large-scale synthetic dataset for different autonomous driving scenarios that includes distinct and rare unknown objects. |
Mennatullah Siam; Alex Kendall; Martin Jagersand; | arxiv-cs.CV | 2021-05-07 |
| 9 | More Separable and Easier to Segment: A Cluster Alignment Method for Cross-Domain Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new UDA semantic segmentation approach based on domain closeness assumption to alleviate the above problems. |
SHUANG WANG et. al. | arxiv-cs.CV | 2021-05-07 |
| 10 | A Novel Falling-Ball Algorithm for Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a novel Falling-Ball algorithm is presented, which is a region-based segmentation algorithm, and an alternative to watershed transform (based on waterfall model). |
Asra Aslam; Ekram Khan; Mohammad Samar Ansari; M. M. Sufyan Beg; | arxiv-cs.CV | 2021-05-06 |
| 11 | Weakly Supervised Pseudo-Label Assisted Learning for ALS Point Cloud Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose a pseudo-label-assisted point cloud segmentation method with very few sparsely sampled labels that are normally randomly selected for each class. |
Puzuo Wang; Wei Yao; | arxiv-cs.CV | 2021-05-05 |
| 12 | Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To align the correct semantic categories across domains, we propose a contrastive learning approach that adapts category-wise centroids across domains. |
Robert A. Marsden; Alexander Bartler; Mario Döbler; Bin Yang; | arxiv-cs.CV | 2021-05-05 |
| 13 | Bayesian Logistic Shape Model Inference: Application to Cochlea Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This framework is applied to the segmentation of cochlea structures from clinical CT images constrained by a 10 parameter shape model. |
WANG ZIHAO et. al. | arxiv-cs.CV | 2021-05-05 |
| 14 | Beyond Self-attention: External Attention Using Two Linear Layers for Visual Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel attention mechanism which we call external attention, based on two external, small, learnable, and shared memories, which can be implemented easily by simply using two cascaded linear layers and two normalization layers; it conveniently replaces self-attention in existing popular architectures. |
Meng-Hao Guo; Zheng-Ning Liu; Tai-Jiang Mu; Shi-Min Hu; | arxiv-cs.CV | 2021-05-05 |
| 15 | Instance Segmentation of Fallen Trees in Aerial Color Infrared Imagery Using Active Multi-contour Evolution with Fully Convolutional Network-based Intensity Priors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a framework for segmenting instances of a common object class by multiple active contour evolution over semantic segmentation maps of images obtained through fully convolutional networks. |
Przemyslaw Polewski; Jacquelyn Shelton; Wei Yao; Marco Heurich; | arxiv-cs.CV | 2021-05-05 |
| 16 | Moving SLAM: Fully Unsupervised Deep Learning in Non-Rigid Scenes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method to train deep networks to decompose videos into 3D geometry (camera and depth), moving objects, and their motions, with no supervision. |
Dan Xu; Andrea Vedaldi; Joao F. Henriques; | arxiv-cs.CV | 2021-05-05 |
| 17 | Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an encoder fusion network (EFN), which transforms the visual encoder into a multi-modal feature learning network, and uses language to refine the multi-modal features progressively. |
Guang Feng; Zhiwei Hu; Lihe Zhang; Huchuan Lu; | arxiv-cs.CV | 2021-05-04 |
| 18 | Computer Vision for Liquid Samples in Hospitals and Medical Labs Using Hierarchical Image Segmentation and Relations Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents a new dataset containing 1,300 annotated images of medical samples involving vessels containing liquids and solid material. |
Sagi Eppel; Haoping Xu; Alan Aspuru-Guzik; | arxiv-cs.CV | 2021-05-04 |
| 19 | Combining Supervised and Un-supervised Learning for Automatic Citrus Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To take advantages of both networks, we employ the multimodal transformer to combine supervised learned static information and unsupervised learned movement information. |
Heqing Huang; Tongbin Huang; Zhen Li; Zhiwei Wei; Shilei Lv; | arxiv-cs.CV | 2021-05-04 |
| 20 | Beyond Pixel-wise Supervision for Segmentation: A Few Global Shape Descriptors Might Be Surprisingly Good! Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce and formulate a few shape descriptors in the context of deep segmentation, and evaluate their potential as standalone losses on two different challenging tasks. |
Hoel Kervadec; Houda Bahig; Laurent Letourneau-Guillon; Jose Dolz; Ismail Ben Ayed; | arxiv-cs.CV | 2021-05-03 |
| 21 | Self-supervised Augmentation Consistency for Adapting Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an approach to domain adaptation for semantic segmentation that is both practical and highly accurate. |
Nikita Araslanov; Stefan Roth; | arxiv-cs.CV | 2021-04-30 |
| 22 | SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we bridge this gap by introducing the SegmentMeIfYouCan benchmark. We provide two corresponding datasets together with a test suite performing an in-depth method analysis, considering both established pixel-wise performance metrics and recent component-wise ones, which are insensitive to object sizes. |
ROBIN CHAN et. al. | arxiv-cs.CV | 2021-04-30 |
| 23 | Reproducibility of FDA: Fourier Domain Adaptation ForSemantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The following paper is a reproducibility report for FDA: Fourier Domain Adaptation for Semantic Segmentation published in the CVPR 2020 as part of the ML Reproducibility Challenge 2020. |
ARNESH KUMAR ISSAR et. al. | arxiv-cs.CV | 2021-04-30 |
| 24 | IPatch: A Remote Adversarial Patch Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a new type of adversarial patch which alters a model’s perception of an image’s semantics. |
Yisroel Mirsky; | arxiv-cs.CV | 2021-04-30 |
| 25 | Improved Real-Time Monocular SLAM Using Semantic Segmentation on Selective Frames Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes an improved real-time monocular SLAM that resolves the aforementioned challenges by efficiently using deep learning-based semantic segmentation. |
Jinkyu Lee; Muhyun Back; Sung Soo Hwang; Il Yong Chun; | arxiv-cs.CV | 2021-04-30 |
| 26 | AttendSeg: A Tiny Attention Condenser Neural Network for Semantic Segmentation on The Edge Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we introduce \textbf{AttendSeg}, a low-precision, highly compact deep neural network tailored for on-device semantic segmentation. |
Xiaoyu Wen; Mahmoud Famouri; Andrew Hryniowski; Alexander Wong; | arxiv-cs.CV | 2021-04-29 |
| 27 | Emerging Properties in Self-Supervised Vision Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets). |
MATHILDE CARON et. al. | arxiv-cs.CV | 2021-04-29 |
| 28 | Crack Semantic Segmentation Using The U-Net with Full Attention Strategy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a novel artificial neural network architecture named Full Attention U-net for image semantic segmentation. |
Fangzheng Lin; Jiesheng Yang; Jiangpeng Shu; Raimar J. Scherer; | arxiv-cs.CV | 2021-04-29 |
| 29 | Pyramid Medical Transformer for Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we developed a novel method to integrate multi-scale attention and CNN feature extraction using a pyramidal network architecture, namely Pyramid Medical Transformer (PMTrans). |
Zhuangzhuang Zhang; Baozhou Sun; Weixiong Zhang; | arxiv-cs.CV | 2021-04-29 |
| 30 | Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose a flexible ensemble-distillation framework for performing semantic segmentation based UDA, allowing any arbitrary composition of the members in the ensemble while still maintaining its superior performance. |
Chen-Hao Chao; Bo-Wun Cheng; Chun-Yi Lee; | arxiv-cs.CV | 2021-04-29 |
| 31 | DeepSatData: Building Large Scale Datasets of Satellite Images for Training Machine Learning Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This report presents design considerations for automatically generating satellite imagery datasets for training machine learning models with emphasis placed on dense classification tasks, e.g. semantic segmentation. |
Michail Tarasiou; Stefanos Zafeiriou; | arxiv-cs.CV | 2021-04-28 |
| 32 | Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we leverage the guidance from self-supervised depth estimation, which is available on both domains, to bridge the domain gap. |
Qin Wang; Dengxin Dai; Lukas Hoyer; Olga Fink; Luc Van Gool; | arxiv-cs.CV | 2021-04-28 |
| 33 | Two Stages for Visual Object Tracking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel tracker with two-stages: detection and segmentation. |
Fei Chen; Xiaodong Wang; | arxiv-cs.CV | 2021-04-28 |
| 34 | Point Cloud Learning with Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a novel framework, called Multi-level Multi-scale Point Transformer (MLMSPT) that works directly on the irregular point clouds for representation learning. |
Xian-Feng Han; Yu-Jia Kuang; Guo-Qiang Xiao; | arxiv-cs.CV | 2021-04-28 |
| 35 | Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from A Class-wise Memory Bank Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents a novel approach for semi-supervised semantic segmentation, i.e., per-pixel classification problem assuming that only a small set of the available data is labeled. |
Inigo Alonso; Alberto Sabater; David Ferstl; Luis Montesano; Ana C. Murillo; | arxiv-cs.CV | 2021-04-27 |
| 36 | Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a semi-weakly supervised segmentation algorithm to overcome this barrier. |
Simon Reiß; Constantin Seibold; Alexander Freytag; Erik Rodner; Rainer Stiefelhagen; | arxiv-cs.CV | 2021-04-27 |
| 37 | Rethinking BiSeNet For Real-time Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To handle these problems, we propose a novel and efficient structure named Short-Term Dense Concatenate network (STDC network) by removing structure redundancy. |
MINGYUAN FAN et. al. | arxiv-cs.CV | 2021-04-27 |
| 38 | ACDC: The Adverse Conditions Dataset with Correspondences for Semantic Driving Scene Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we introduce ACDC, the Adverse Conditions Dataset with Correspondences for training and testing semantic segmentation methods on adverse visual conditions. |
Christos Sakaridis; Dengxin Dai; Luc Van Gool; | arxiv-cs.CV | 2021-04-27 |
| 39 | MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve these problems, we propose a novel deep learning-based interactive segmentation method that not only has high efficiency due to only requiring clicks as user inputs but also generalizes well to a range of previously unseen objects. |
XIANGDE LUO et. al. | arxiv-cs.CV | 2021-04-25 |
| 40 | Transformer Meets DCFAM: A Novel Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By contrast, we introduce the Swin Transformer as the backbone to fully extract the context information and design a novel decoder named densely connected feature aggregation module (DCFAM) to restore the resolution and generate the segmentation map. |
Libo Wang; Rui Li; Chenxi Duan; Xiaoliang Meng; Shenghui Fang; | arxiv-cs.CV | 2021-04-25 |
| 41 | Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel heterogeneous grid convolution that builds a graph-based image representation by exploiting heterogeneity in the image content, enabling adaptive, efficient, and controllable computations in a convolutional architecture. |
Ryuhei Hamaguchi; Yasutaka Furukawa; Masaki Onishi; Ken Sakurada; | arxiv-cs.CV | 2021-04-22 |
| 42 | Semi-Supervised Segmentation of Concrete Aggregate Using Consensus Regularisation and Prior Guidance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome the limitations of standard consistency training, we propose a novel semi-supervised framework for semantic segmentation, introducing additional losses based on prior knowledge. |
Max Coenen; Tobias Schack; Dries Beyer; Christian Heipke; Michael Haist; | arxiv-cs.CV | 2021-04-22 |
| 43 | Pri3D: Can 3D Priors Help 2D Representation Learning? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce an approach to learn view-invariant,geometry-aware representations for network pre-training, based on multi-view RGB-D data, that can then be effectively transferred to downstream 2D tasks. |
Ji Hou; Saining Xie; Benjamin Graham; Angela Dai; Matthias Nießner; | arxiv-cs.CV | 2021-04-22 |
| 44 | Domain Adaptation for Semantic Segmentation Via Patch-Wise Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a novel approach to unsupervised and semi-supervised domain adaptation for semantic segmentation. |
WEIZHE LIU et. al. | arxiv-cs.CV | 2021-04-22 |
| 45 | DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel domain adaptation network (DANNet) for nighttime semantic segmentation without using labeled nighttime image data. |
Xinyi Wu; Zhenyao Wu; Hao Guo; Lili Ju; Song Wang; | arxiv-cs.CV | 2021-04-21 |
| 46 | BEVDetNet: Bird’s Eye View LiDAR Point Cloud Based Real-time 3D Object Detection for Autonomous Driving Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to develop a very low latency algorithm with fixed runtime. |
Sambit Mohapatra; Senthil Yogamani; Heinrich Gotzig; Stefan Milz; Patrick Mader; | arxiv-cs.CV | 2021-04-21 |
| 47 | Comprehensive Multi-Modal Interactions for Referring Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a Joint Reasoning (JRM) module and a novel Cross-Modal Multi-Level Fusion (CMMLF) module for tackling this task. |
Kanishk Jain; Vineet Gandhi; | arxiv-cs.CV | 2021-04-21 |
| 48 | Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel guided interactive segmentation (GIS) algorithm for video objects to improve the segmentation accuracy and reduce the interaction time. |
Yuk Heo; Yeong Jun Koh; Chang-Su Kim; | arxiv-cs.CV | 2021-04-21 |
| 49 | Camouflaged Object Segmentation with Distraction Mining Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we strive to embrace challenges towards effective and efficient COS. |
HAIYANG MEI et. al. | arxiv-cs.CV | 2021-04-21 |
| 50 | Flow-based Video Segmentation for Human Head and Shoulders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome the motion blur problem in video segmentation, we propose a novel flow-based encoder-decoder network (FUNet) that combines both traditional Horn-Schunck optical-flow estimation technique and convolutional neural networks to perform robust real-time video segmentation. We also introduce a video and image segmentation dataset: ConferenceVideoSegmentationDataset. |
Zijian Kuang; Xinran Tie; | arxiv-cs.CV | 2021-04-20 |
| 51 | Superpixels and Graph Convolutional Neural Networks for Efficient Detection of Nutrient Deficiency Stress from Aerial Imagery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast, we propose a much lighter graph-based method to perform node-based classification. |
Saba Dadsetan; David Pichler; David Wilson; Naira Hovakimyan; Jennifer Hobbs; | arxiv-cs.CV | 2021-04-20 |
| 52 | GENESIS-V2: Inferring Unordered Object Representations Without Iterative Refinement Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast to established paradigms, this work proposes an embedding-based approach in which embeddings of pixels are clustered in a differentiable fashion using a stochastic, non-parametric stick-breaking process. |
Martin Engelcke; Oiwi Parker Jones; Ingmar Posner; | arxiv-cs.CV | 2021-04-20 |
| 53 | CTNet: Context-based Tandem Network for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes a novel Context-based Tandem Network (CTNet) by interactively exploring the spatial contextual information and the channel contextual information, which can discover the semantic context for semantic segmentation. |
Zechao Li; Yanpeng Sun; Jinhui Tang; | arxiv-cs.CV | 2021-04-20 |
| 54 | Semantic Segmentation By Improved Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, an improved Generative Adversarial Networks (GANs) for image semantic segmentation task (semantic segmentation by GANs, Seg-GAN) is proposed to facilitate further segmentation research. |
ZENGSHUN ZHAOA et. al. | arxiv-cs.CV | 2021-04-20 |
| 55 | Plants Don’t Walk on The Street: Common-Sense Reasoning for Reliable Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to use a partly human-designed, partly learned set of rules to describe relations between objects of a traffic scene on a high level of abstraction. |
LINARA ADILOVA et. al. | arxiv-cs.CV | 2021-04-19 |
| 56 | SCNet: Enhancing Few-Shot Semantic Segmentation By Self-Contrastive Background Prototypes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, in this paper, we introduce a complementary self-contrastive task into few-shot semantic segmentation. |
JIACHENG CHEN et. al. | arxiv-cs.CV | 2021-04-19 |
| 57 | Gaussian Dynamic Convolution for Efficient Single-Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on the single-image segmentation problem only with some seeds such as scribbles. |
XIN SUN et. al. | arxiv-cs.CV | 2021-04-18 |
| 58 | Learning Fuzzy Clustering for SPECT/CT Segmentation Via Convolutional Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes a fast and robust automated segmentation method for partitioning a QBSPECT image into lesion, bone, and background. |
JUNYU CHEN et. al. | arxiv-cs.CV | 2021-04-17 |
| 59 | A De-raining Semantic Segmentation Network for Real-time Foreground Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Few researches have been proposed specifically for real-time semantic segmentation in rainy environments. |
Fanyi Wang; Yihui Zhang; | arxiv-cs.CV | 2021-04-16 |
| 60 | Street-Map Based Validation of Semantic Segmentation in Autonomous Driving Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Besides the validation approach, we present a method to correct the vehicle’s GPS position so that a more accurate localization can be used for the street-map based validation. |
LAURA VON RUEDEN et. al. | arxiv-cs.CV | 2021-04-15 |
| 61 | Self-supervised Video Object Segmentation By Motion Grouping Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we work towards developing a computer vision system able to segment objects by exploiting motion cues, i.e. motion segmentation. |
Charig Yang; Hala Lamdouar; Erika Lu; Andrew Zisserman; Weidi Xie; | arxiv-cs.CV | 2021-04-15 |
| 62 | A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the success of semi-supervised learning methods in image classification, here we propose a simple yet effective semi-supervised learning framework for semantic segmentation. |
Jianlong Yuan; Yifan Liu; Chunhua Shen; Zhibin Wang; Hao Li; | arxiv-cs.CV | 2021-04-15 |
| 63 | SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to reduce the number of annotated labels, we propose a semi-supervised semantic point cloud segmentation network, named SSPC-Net, where we train the semantic segmentation network by inferring the labels of unlabeled points from the few annotated 3D points. |
Mingmei Cheng; Le Hui; Jin Xie; Jian Yang; | arxiv-cs.CV | 2021-04-15 |
| 64 | Adaptive Intermediate Representations for Video Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a new way to leverage semantic segmentation as an intermediate representation for video understanding and use it in a way that requires no additional labeling. |
Juhana Kangaspunta; AJ Piergiovanni; Rico Jonschkowski; Michael Ryoo; Anelia Angelova; | arxiv-cs.CV | 2021-04-14 |
| 65 | ComBiNet: Compact Convolutional Bayesian Neural Network for Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we tackle two defects that hinder their deployment in real-world applications: 1) Predictions lack uncertainty quantification that may be crucial to many decision making systems; 2) Large memory storage and computational consumption demanding extensive hardware resources. |
Martin Ferianc; Divyansh Manocha; Hongxiang Fan; Miguel Rodrigues; | arxiv-cs.CV | 2021-04-14 |
| 66 | Image Manipulation Detection By Multi-View Multi-Scale Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we address both aspects by multi-view feature learning and multi-scale supervision. |
Xinru Chen; Chengbo Dong; Jiaqi Ji; Juan Cao; Xirong Li; | arxiv-cs.CV | 2021-04-14 |
| 67 | Learning Structure-aware Semantic Segmentation with Image-level Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that the lost structure information in CAM limits its application in downstream semantic segmentation, leading to deteriorated predictions. |
Jiawei Liu; Jing Zhang; Yicong Hong; Nick Barnes; | arxiv-cs.CV | 2021-04-14 |
| 68 | Interpretability-Driven Sample Selection Using Self Supervised Learning For Disease Classification And Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose a novel sample selection methodology based on deep features leveraging information contained in interpretability saliency maps. |
Dwarikanath Mahapatra; | arxiv-cs.CV | 2021-04-13 |
| 69 | All You Need Are A Few Pixels: Semantic Segmentation with PixelPick Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that in order to achieve a good level of segmentation performance, all you need are a few well-chosen pixel labels. |
Gyungin Shin; Weidi Xie; Samuel Albanie; | arxiv-cs.CV | 2021-04-13 |
| 70 | Single Image Depth Estimation: An Overview Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We review solutions to the problem of depth estimation, arguably the most important subtask in scene understanding. |
Alican Mertan; Damien Jade Duff; Gozde Unal; | arxiv-cs.CV | 2021-04-13 |
| 71 | DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce DatasetGAN: an automatic procedure to generate massive datasets of high-quality semantically segmented images requiring minimal human effort. To showcase the power of our approach, we generated datasets for 7 image segmentation tasks which include pixel-level labels for 34 human face parts, and 32 car parts. |
YUXUAN ZHANG et. al. | arxiv-cs.CV | 2021-04-13 |
| 72 | Machine-learned 3D Building Vectorization from Satellite Imagery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a machine learning based approach for automatic 3D building reconstruction and vectorization. |
Yi Wang; Stefano Zorzi; Ksenia Bittner; | arxiv-cs.CV | 2021-04-13 |
| 73 | Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel framework for discriminative pixel-level tasks using a generative model of both images and labels. |
Daiqing Li; Junlin Yang; Karsten Kreis; Antonio Torralba; Sanja Fidler; | arxiv-cs.CV | 2021-04-12 |
| 74 | Spatially Varying Label Smoothing: Capturing Uncertainty from Expert Annotations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose Spatially Varying Label Smoothing (SVLS), a soft labeling technique that captures the structural uncertainty in semantic segmentation. |
Mobarakol Islam; Ben Glocker; | arxiv-cs.CV | 2021-04-12 |
| 75 | Predicting Pedestrian Crossing Intention with Feature Fusion and Spatio-Temporal Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work addresses the above limitations by introducing a novel neural network architecture to fuse inherently different spatio-temporal features for pedestrian crossing intention prediction. |
Dongfang Yang; Haolin Zhang; Ekim Yurtsever; Keith Redmill; Ümit Özgüner; | arxiv-cs.CV | 2021-04-12 |
| 76 | Door Delivery of Packages Using Drones Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a system that enables delivery drones to autonomously navigate and deliver packages at various locations around the house. |
Shyam Sundar Kannan; Byung-Cheol Min; | arxiv-cs.RO | 2021-04-12 |
| 77 | An MRF-UNet Product of Experts for Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to fuse both strategies by computing the product of distributions of a UNet and an MRF. |
MIKAEL BRUDFORS et. al. | arxiv-cs.CV | 2021-04-12 |
| 78 | Improving Online Performance Prediction for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we address the task of observing the performance of a semantic segmentation deep neural network (DNN) during online operation, i.e., during inference, which is of high importance in safety-critical applications such as autonomous driving. |
Marvin Klingner; Andreas Bär; Marcel Mross; Tim Fingscheidt; | arxiv-cs.CV | 2021-04-12 |
| 79 | Two Layer Ensemble of Deep Learning Models for Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a two-layer ensemble of deep learning models for the segmentation of medical images. |
Truong Dang; Tien Thanh Nguyen; John McCall; Eyad Elyan; Carlos Francisco Moreno-García; | arxiv-cs.CV | 2021-04-10 |
| 80 | Ensemble Learning Based on Classifier Prediction Confidence and Comprehensive Learning Particle Swarm Optimisation for Polyp Localisation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce an ensemble of medical polyp segmentation algorithms. |
Truong Dang; Thanh Nguyen; John McCall; Alan Wee-Chung Liew; | arxiv-cs.CV | 2021-04-10 |
| 81 | Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we introduce a novel approach for more accurate and efficient spatio-temporal segmentation. |
Tianfei Zhou; Jianwu Li; Xueyi Li; Ling Shao; | arxiv-cs.CV | 2021-04-10 |
| 82 | SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds with 1000x Fewer Labels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a new weak supervision method to implicitly augment the total amount of available supervision signals, by leveraging the semantic similarity between neighboring points. |
QINGYONG HU et. al. | arxiv-cs.CV | 2021-04-10 |
| 83 | Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present, UVO (Unidentified Video Objects), a new benchmark for open-world class-agnostic object segmentation in videos. |
Weiyao Wang; Matt Feiszli; Heng Wang; Du Tran; | arxiv-cs.CV | 2021-04-10 |
| 84 | Estimation of BMI from Facial Images Using Semantic Segmentation Based Region-Aware Pooling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to use deep features that are pooled from different face regions (eye, nose, eyebrow, lips, etc.,) and demonstrate that this explicit pooling from face regions can significantly boost the performance of BMI prediction. |
Nadeem Yousaf; Sarfaraz Hussein; Waqas Sultani; | arxiv-cs.CV | 2021-04-10 |
| 85 | Context-self Contrastive Pretraining for Crop Type Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose a fully-supervised pretraining scheme based on contrastive learning particularly tailored to dense classification tasks. |
Michail Tarasiou; Riza Alp Guler; Stefanos Zafeiriou; | arxiv-cs.CV | 2021-04-09 |
| 86 | Learning Position and Target Consistency for Memory-based Video Object Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this limitation, we propose to Learn position and target Consistency framework for Memory-based video object segmentation, termed as LCM. |
LI HU et. al. | arxiv-cs.CV | 2021-04-09 |
| 87 | Bootstrapping Semantic Segmentation with Regional Contrast Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. |
Shikun Liu; Shuaifeng Zhi; Edward Johns; Andrew J. Davison; | arxiv-cs.CV | 2021-04-09 |
| 88 | A Bayesian Approach to Reinforcement Learning of Vision-Based Vehicular Control Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a state-of-the-art reinforcement learning method for autonomous driving. |
Zahra Gharaee; Karl Holmquist; Linbo He; Michael Felsberg; | arxiv-cs.CV | 2021-04-08 |
| 89 | Progressive Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The objective of this work is to segment high-resolution images without overloading GPU memory usage or losing the fine details in the output segmentation map. |
Chuong Huynh; Anh Tran; Khoa Luu; Minh Hoai; | arxiv-cs.CV | 2021-04-08 |
| 90 | Few-Shot Meta-Learning on Point Cloud for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The paper proposes a semantic segmentation method for point cloud based on meta-learning. |
Xudong Li; Li Feng; Lei Li; Chen Wang; | arxiv-cs.RO | 2021-04-07 |
| 91 | Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce feature-level space-shaping regularization strategies to reduce the domain discrepancy in semantic segmentation. |
Francesco Barbato; Marco Toldo; Umberto Michieli; Pietro Zanuttigh; | arxiv-cs.CV | 2021-04-06 |
| 92 | Weakly Supervised Segmentation with Cross-modality Equivariant Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel learning strategy that leverages self-supervision in a multi-modal image scenario to significantly enhance original CAMs. |
Gaurav Patel; Jose Dolz; | arxiv-cs.CV | 2021-04-06 |
| 93 | InverseForm: A Loss Function for Structured Boundary-Aware Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel boundary-aware loss term for semantic segmentation using an inverse-transformation network, which efficiently learns the degree of parametric transformations between estimated and target boundaries. |
Shubhankar Borse; Ying Wang; Yizhe Zhang; Fatih Porikli; | arxiv-cs.CV | 2021-04-06 |
| 94 | DCANet: Dense Context-Aware Network for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast to some previous works utilizing the multi-scale context fusion, we propose a novel module, named Dense Context-Aware (DCA) module, to adaptively integrate local detail information with global dependencies. |
Yifu Liu; Chenfeng Xu; Xinyu Jin; | arxiv-cs.CV | 2021-04-06 |
| 95 | Robust Trust Region for Weakly Supervised Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new robust trust region approach for regularized losses improving the state-of-the-art results. |
Dmitrii Marin; Yuri Boykov; | arxiv-cs.CV | 2021-04-05 |
| 96 | One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To leverage these extremely sparse labels in network training, we design a novel self-training approach, in which we iteratively conduct the training and label propagation, facilitated by a graph propagation module. |
Zhengzhe Liu; Xiaojuan Qi; Chi-Wing Fu; | arxiv-cs.CV | 2021-04-05 |
| 97 | 3D-to-2D Distillation for Indoor Scene Parsing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Going beyond prior works that leverage geometry information, typically paired depth maps, we present a new approach, a 3D-to-2D distillation framework, that enables us to leverage 3D features extracted from large-scale 3D data repository (e.g., ScanNet-v2) to enhance 2D features extracted from RGB images. |
Zhengzhe Liu; Xiaojuan Qi; Chi-Wing Fu; | arxiv-cs.CV | 2021-04-05 |
| 98 | Hierarchical Pyramid Representations for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we design novel hierarchical, contextual, and multiscale pyramidal representations to capture the properties from an input image. |
Hiroaki Aizawa; Yukihiro Domae; Kunihito Kato; | arxiv-cs.CV | 2021-04-05 |
| 99 | Potential Convolution: Embedding Point Clouds Into Potential Fields Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, rather than defining a continuous or discrete kernel, we directly embed convolutional kernels into the learnable potential fields, giving rise to potential convolution. |
DENGSHENG CHEN et. al. | arxiv-cs.CV | 2021-04-04 |
| 100 | Hypercorrelation Squeeze for Few-Shot Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the problem, we propose Hypercorrelation Squeeze Networks (HSNet) that leverages multi-level feature correlation and efficient 4D convolutions. |
Juhong Min; Dahyun Kang; Minsu Cho; | arxiv-cs.CV | 2021-04-04 |
| 101 | Weakly-supervised Instance Segmentation Via Class-agnostic Learning with Salient Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The BoxCaseg model is jointly trained using box-supervised images and salient images in a multi-task learning manner. |
XINGGANG WANG et. al. | arxiv-cs.CV | 2021-04-03 |
| 102 | Decomposing 3D Scenes Into Objects Via Unsupervised Volume Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present ObSuRF, a method which turns a single image of a scene into a 3D model represented as a set of Neural Radiance Fields (NeRFs), with each NeRF corresponding to a different object. |
Karl Stelzner; Kristian Kersting; Adam R. Kosiorek; | arxiv-cs.CV | 2021-04-02 |
| 103 | Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To implement this idea, we propose a novel pooling method, dubbed background-aware pooling (BAP), that focuses more on aggregating foreground features inside the bounding boxes using attention maps. |
Youngmin Oh; Beomjun Kim; Bumsub Ham; | arxiv-cs.CV | 2021-04-02 |
| 104 | Confidence Adaptive Anytime Pixel-Level Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the first unified and end-to-end model approach for anytime pixel-level recognition. |
Zhuang Liu; Trevor Darrell; Evan Shelhamer; | arxiv-cs.CV | 2021-04-01 |
| 105 | Half-Real Half-Fake Distillation for Class-Incremental Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To avoid setting detailed pixel-wise segmentation maps as the supervision manually, we propose the SegInversion to synthesize images using the image-level labels. |
ZILONG HUANG et. al. | arxiv-cs.CV | 2021-04-01 |
| 106 | MeanShift++: Extremely Fast Mode-Seeking With Applications to Segmentation and Object Tracking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose MeanShift++, an extremely fast mode-seeking algorithm based on MeanShift that uses a grid-based approach to speed up the mean shift step, replacing the computationally expensive neighbors search with a density-weighted mean of adjacent grid cells. |
Jennifer Jang; Heinrich Jiang; | arxiv-cs.CV | 2021-04-01 |
| 107 | Linear Semantics in Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to better understand the semantic representation of GANs, and thereby enable semantic control in GAN’s generation process. |
Jianjin Xu; Changxi Zheng; | arxiv-cs.CV | 2021-04-01 |
| 108 | Unsupervised Foreground-Background Segmentation with Equivariant Layered GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an unsupervised foreground-background segmentation method via training a segmentation network on the synthetic pseudo segmentation dataset generated from GANs, which are trained from a collection of images without annotations to explicitly disentangle foreground and background. |
Yu Yang; Hakan Bilen; Qiran Zou; Wing Yin Cheung; Xiangyang Ji; | arxiv-cs.CV | 2021-04-01 |
| 109 | Deep Ensembles Based on Stochastic Activation Selection for Polyp Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we compare some variant of the DeepLab architecture obtained by varying the decoder backbone. |
Alessandra Lumini; Loris Nanni; Gianluca Maguolo; | arxiv-cs.CV | 2021-04-01 |
| 110 | The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the task of semi-supervised semantic segmentation, where we aim to produce pixel-wise semantic object masks given only a small number of human-labeled training examples. |
EU WERN TEH et. al. | arxiv-cs.CV | 2021-03-31 |
| 111 | Camouflaged Instance Segmentation: Dataset and Benchmark Suite Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To promote the new task of camouflaged instance segmentation, we introduce a new large-scale dataset, namely CAMO++, by extending our preliminary CAMO dataset (camouflaged object segmentation) in terms of quantity and diversity. |
TRUNG-NGHIA LE et. al. | arxiv-cs.CV | 2021-03-31 |
| 112 | Learning Domain Adaptation with Model Calibration for Surgical Report Generation in Robotic Surgery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For this purpose, we develop a multi-layer transformer-based model with the gradient reversal adversarial learning to generate a caption for the multi-domain surgical images that can describe the semantic relationship between instruments and surgical Region of Interest (ROI). We annotate two robotic surgery datasets of MICCAI robotic scene segmentation and Transoral Robotic Surgery (TORS) with the captions of procedures and empirically show that our proposed method improves the performance in both source and target domain surgical reports generation in the manners of unsupervised, zero-shot, one-shot, and few-shot learning. |
Mengya Xu; Mobarakol Islam; Chwee Ming Lim; Hongliang Ren; | arxiv-cs.RO | 2021-03-31 |
| 113 | Fusing RGBD Tracking and Segmentation Tree Sampling for Multi-Hypothesis Volumetric Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose Multihypothesis Segmentation Tracking (MST), a novel method for volumetric segmentation in changing scenes, which allows scene ambiguity to be tracked and our estimates to be adjusted over time as we interact with the scene. |
Andrew Price; Kun Huang; Dmitry Berenson; | arxiv-cs.RO | 2021-03-31 |
| 114 | Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead of following the previous literature, we propose to learn correspondence using Video Frame-level Similarity (VFS) learning, i.e, simply learning from comparing video frames. |
Jiarui Xu; Xiaolong Wang; | arxiv-cs.CV | 2021-03-31 |
| 115 | FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we leverage the information of each training epoch to prune the prediction maps of the subsequent epochs. |
NIKHIL KUMAR TOMAR et. al. | arxiv-cs.CV | 2021-03-31 |
| 116 | Evaluation of Multimodal Semantic Segmentation Using RGB-D Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our goal is to develop stable, accurate, and robust semantic scene understanding methods for wide-area scene perception and understanding, especially in challenging outdoor environments. |
Jiesi Hu; Ganning Zhao; Suya You; C. C. Jay Kuo; | arxiv-cs.CV | 2021-03-30 |
| 117 | Weakly-Supervised Image Semantic Segmentation Using Graph Convolutional Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this issue, we propose a Graph Convolutional Network (GCN)-based feature propagation framework. |
Shun-Yi Pan; Cheng-You Lu; Shih-Po Lee; Wen-Hsiao Peng; | arxiv-cs.CV | 2021-03-30 |
| 118 | Topology-Preserving 3D Image Segmentation Based On Hyperelastic Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel 3D topology-preserving registration-based segmentation model with the hyperelastic regularization, which can handle both 2D and 3D images. |
Daoping Zhang; Lok Ming Lui; | arxiv-cs.CV | 2021-03-30 |
| 119 | Geometric Unsupervised Domain Adaptation for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to use self-supervised monocular depth estimation as a proxy task to bridge this gap and improve sim-to-real unsupervised domain adaptation (UDA). |
Vitor Guizilini; Jie Li; Rares Ambrus; Adrien Gaidon; | arxiv-cs.CV | 2021-03-30 |
| 120 | Exploiting Invariance in Training Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. |
CHENGXI YE et. al. | arxiv-cs.CV | 2021-03-30 |
| 121 | Distribution Alignment: A Unified Framework for Long-tail Visual Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by our discovery, we propose a unified distribution alignment strategy for long-tail visual recognition. |
Songyang Zhang; Zeming Li; Shipeng Yan; Xuming He; Jian Sun; | arxiv-cs.CV | 2021-03-30 |
| 122 | Source-Free Domain Adaptation for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To cope with this issue, we propose a source-free domain adaptation framework for semantic segmentation, namely SFDA, in which only a well-trained source model and an unlabeled target domain dataset are available for adaptation. |
Yuang Liu; Wei Zhang; Jun Wang; | arxiv-cs.CV | 2021-03-30 |
| 123 | Is Segmentation Uncertainty Useful? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider two common use cases of segmentation uncertainty, namely assessment of segmentation quality and active learning. |
Steffen Czolbe; Kasra Arnavaz; Oswin Krause; Aasa Feragen; | arxiv-cs.CV | 2021-03-30 |
| 124 | Multi-View Radar Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose several novel architectures, and their associated losses, which analyse multiple views of the range-angle-Doppler radar tensor to segment it semantically. |
Arthur Ouaknine; Alasdair Newson; Patrick Pérez; Florence Tupin; Julien Rebut; | arxiv-cs.CV | 2021-03-30 |
| 125 | Self-Guided and Cross-Guided Learning for Few-Shot Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a simple but effective self-guided learning approach, where the lost critical information is mined. |
Bingfeng Zhang; Jimin Xiao; Terry Qin; | arxiv-cs.CV | 2021-03-30 |
| 126 | Locate Then Segment: A Strong Pipeline for Referring Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Previous methods usually focus on designing an implicit and recurrent feature interaction mechanism to fuse the visual-linguistic features to directly generate the final segmentation mask without explicitly modeling the localization information of the referent instances. |
YA JING et. al. | arxiv-cs.CV | 2021-03-30 |
| 127 | Physics-based Differentiable Depth Sensor Simulation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a novel end-to-end differentiable simulation pipeline for the generation of realistic 2.5D scans, built on physics-based 3D rendering and custom block-matching algorithms. |
Benjamin Planche; Rajat Vikram Singh; | arxiv-cs.CV | 2021-03-30 |
| 128 | Boundary IoU: Improving Object-Centric Image Segmentation Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Boundary IoU (Intersection-over-Union), a new segmentation evaluation measure focused on boundary quality. |
Bowen Cheng; Ross Girshick; Piotr Dollár; Alexander C. Berg; Alexander Kirillov; | arxiv-cs.CV | 2021-03-30 |
| 129 | RobustNet: Improving Domain Generalization in Urban-Scene Segmentation Via Instance Selective Whitening Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, this paper proposes a novel instance selective whitening loss to improve the robustness of the segmentation networks for unseen domains. |
SUNGHA CHOI et. al. | arxiv-cs.CV | 2021-03-29 |
| 130 | Get Away from Style: Category-Guided Domain Adaptation for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on UDA for semantic segmentation task. |
Yantian Luo; Zhiming Wang; Danlan Huang; Ning Ge; Jianhua Lu; | arxiv-cs.CV | 2021-03-29 |
| 131 | Enhanced Boundary Learning for Glass-like Object Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper aims to solve the glass-like object segmentation problem via enhanced boundary learning. |
HAO HE et. al. | arxiv-cs.CV | 2021-03-29 |
| 132 | Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose one efficient bootstrapping method, called Adaboost Student, explicitly learning complementary models during training and liberating users from empirical early stopping. |
Zhedong Zheng; Yi Yang; | arxiv-cs.CV | 2021-03-29 |
| 133 | DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on three important aspects of NAS in 3D medical image segmentation: flexible multi-path network topology, high search efficiency, and budgeted GPU memory usage. |
Yufan He; Dong Yang; Holger Roth; Can Zhao; Daguang Xu; | arxiv-cs.CV | 2021-03-29 |
| 134 | Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose simple yet effective improvements in point representations and local neighborhood graph construction within the general framework of graph neural networks (GNNs) for 3D point cloud processing. |
Siddharth Srivastava; Gaurav Sharma; | arxiv-cs.CV | 2021-03-28 |
| 135 | Instance Segmentation with The Number of Clusters Incorporated in Embedding Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to embed prior clustering information into an embedding learning framework FCRNet, stimulating the one-stage instance segmentation. |
Jianfeng Cao; Hong Yan; | arxiv-cs.CV | 2021-03-27 |
| 136 | An Efficiently Coupled Shape and Appearance Prior for Active Contour Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel training model based on shape and appearance features for object segmentation in images and videos. |
Martin Mueller; Navdeep Dahiya; Anthony Yezzi; | arxiv-cs.CV | 2021-03-27 |
| 137 | Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a fast and robust LiDAR point cloud panoptic segmentation framework, referred to as Panoptic-PolarNet. |
Zixiang Zhou; Yang Zhang; Hassan Foroosh; | arxiv-cs.CV | 2021-03-27 |
| 138 | Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a non-salient region object mining approach for weakly supervised semantic segmentation. |
YAZHOU YAO et. al. | arxiv-cs.CV | 2021-03-26 |
| 139 | Input-Output Balanced Framework for Long-tailed LiDAR Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an input-output balanced framework to handle the issue of long-tailed distribution. |
Peishan Cong; Xinge Zhu; Yuexin Ma; | arxiv-cs.CV | 2021-03-26 |
| 140 | Bidirectional Projection Network for Cross Dimension Scene Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a \emph{bidirectional projection network (BPNet)} for joint 2D and 3D reasoning in an end-to-end manner. |
Wenbo Hu; Hengshuang Zhao; Li Jiang; Jiaya Jia; Tien-Tsin Wong; | arxiv-cs.CV | 2021-03-26 |
| 141 | Spirit Distillation: Precise Real-time Semantic Segmentation of Road Scenes with Insufficient Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the ideas of Fine-tuning-based Transfer Learning (FTT) and feature-based knowledge distillation, we propose a new knowledge distillation method for cross-domain knowledge transference and efficient data-insufficient network training, named Spirit Distillation(SD), which allow the student network to mimic the teacher network to extract general features, so that a compact and accurate student network can be trained for real-time semantic segmentation of road scenes. |
ZHIYUAN WU et. al. | arxiv-cs.CV | 2021-03-25 |
| 142 | Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. |
ZE LIU et. al. | arxiv-cs.CV | 2021-03-25 |
| 143 | Tilted Cross Entropy (TCE): Promoting Fairness in Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the recently introduced tilted ERM (TERM), we propose tilted cross-entropy (TCE) loss and adapt it to the semantic segmentation setting to minimize performance disparity among target classes and promote fairness. |
Attila Szabo; Hadi Jamali-Rad; Siva-Datta Mannava; | arxiv-cs.CV | 2021-03-25 |
| 144 | Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Most existing approaches aim to generate accurate pixel-level labels from weak supervisions. |
Rumeng Yi; Yaping Huang; Qingji Guan; Mengyang Pu; Runsheng Zhang; | arxiv-cs.CV | 2021-03-25 |
| 145 | Factors of Influence for Transfer Learning Across Diverse Appearance Domains and Task Types Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we carry out an extensive experimental exploration of transfer learning across vastly different image domains (consumer photos, autonomous driving, aerial imagery, underwater, indoor scenes, synthetic, close-ups) and task types (semantic segmentation, object detection, depth estimation, keypoint detection). |
Thomas Mensink; Jasper Uijlings; Alina Kuznetsova; Michael Gygli; Vittorio Ferrari; | arxiv-cs.CV | 2021-03-24 |
| 146 | Learning Versatile Neural Architectures By Propagating Network Codes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We solve this challenge by proposing Network Coding Propagation (NCP), a novel neural predictor, which is able to predict an architecture’s performance in multiple datasets and tasks. |
MINGYU DING et. al. | arxiv-cs.CV | 2021-03-24 |
| 147 | A Fine-Grained Dataset and Its Efficient Semantic Segmentation for Unstructured Driving Scenarios Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce TAS500, a novel semantic segmentation dataset for autonomous driving in unstructured environments. |
Kai A. Metzger; Peter Mortimer; Hans-Joachim Wuensche; | arxiv-cs.CV | 2021-03-24 |
| 148 | DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present DRANet, a network architecture that disentangles image representations and transfers the visual attributes in a latent space for unsupervised cross-domain adaptation. |
Seunghun Lee; Sunghyun Cho; Sunghoon Im; | arxiv-cs.CV | 2021-03-24 |
| 149 | MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a novel multi-level adversarial network (MLAN) that aims to address inter-domain inconsistency at both global image level and local region level optimally. |
Jiaxing Huang; Dayan Guan; Shijian Lu; Aoran Xiao; | arxiv-cs.CV | 2021-03-24 |
| 150 | MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we devise a novel lightweight network using a multi-scale context fusion (MSCFNet) scheme, which explores an asymmetric encoder-decoder architecture to dispose this problem. |
GUANGWEI GAO et. al. | arxiv-cs.CV | 2021-03-24 |
| 151 | Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel UDA pipeline that unifies image-level alignment and category-level feature distribution regularization in a coarse-to-fine manner. |
Haoyu Ma; Xiangru Lin; Zifeng Wu; Yizhou Yu; | arxiv-cs.CV | 2021-03-24 |
| 152 | Test-Time Training for Deformable Multi-Scale Image Registration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we construct a test-time training for deep deformable image registration to improve the generalization ability of conventional learning-based registration model. |
WENTAO ZHU et. al. | arxiv-cs.CV | 2021-03-24 |
| 153 | Evidential Fully Convolutional Network for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a hybrid architecture composed of a fully convolutional network (FCN) and a Dempster-Shafer layer for image semantic segmentation. |
Zheng Tong; Philippe Xu; Thierry Denœux; | arxiv-cs.CV | 2021-03-24 |
| 154 | OFFSEG: A Semantic Segmentation Framework For Off-Road Driving Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these issues we propose a framework for off-road semantic segmentation called as OFFSEG that involves (i) a pooled class semantic segmentation with four classes (sky, traversable region, non-traversable region and obstacle) using state-of-the-art deep learning architectures (ii) a colour segmentation methodology to segment out specific sub-classes (grass, puddle, dirt, gravel, etc.) from the traversable region for better scene understanding. |
Kasi Viswanath; Kartikeya Singh; Peng Jiang; Sujit P. B.; Srikanth Saripalli; | arxiv-cs.CV | 2021-03-23 |
| 155 | Deep Neural Networks Learn Meta-Structures to Segment Fluorescence Microscopy Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the learning behavior of DNNs trained by random labels and the characteristics of meta-structures, we propose an unsupervised segmentation model. |
Yaoru Luo; Guole Liu; Wenjing Li; Yuanhao Guo; Ge Yang; | arxiv-cs.CV | 2021-03-22 |
| 156 | Dilated SpineNet for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we evaluate this meta-architecture design on semantic segmentation – another vision task that benefits from high spatial resolution and multi-scale feature fusion at different network stages. |
Abdullah Rashwan; Xianzhi Du; Xiaoqi Yin; Jing Li; | arxiv-cs.CV | 2021-03-22 |
| 157 | CFPNet: Channel-wise Feature Pyramid for Real-Time Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Channel-wise Feature Pyramid (CFP) module to balance those factors. |
Ange Lou; Murray Loew; | arxiv-cs.CV | 2021-03-22 |
| 158 | TICaM: A Time-of-flight In-car Cabin Monitoring Dataset Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present TICaM, a Time-of-flight In-car Cabin Monitoring dataset for vehicle interior monitoring using a single wide-angle depth camera. Additional to real recordings, we provide a synthetic dataset of in-car cabin images with same multi-modality of images and annotations, providing a unique and extremely beneficial combination of synthetic and real data for effectively training cabin monitoring systems and evaluating domain adaptation approaches. |
JIGYASA SINGH KATROLIA et. al. | arxiv-cs.CV | 2021-03-22 |
| 159 | Cross-Dataset Collaborative Learning for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a simple, flexible, and general method for semantic segmentation, termed Cross-Dataset Collaborative Learning (CDCL). |
Li Wang; Dong Li; Yousong Zhu; Lu Tian; Yi Shan; | arxiv-cs.CV | 2021-03-21 |
| 160 | MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a method to encode vital scene semantics such as traversable paths, unexplored areas, and observed scene objects — alongside raw visual streams such as RGB, depth, and semantic segmentation masks — into a semantically informed, top-down egocentric map representation. |
ZACHARY SEYMOUR et. al. | arxiv-cs.CV | 2021-03-21 |
| 161 | A Novel Upsampling and Context Convolution for Image Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a dense upsampling convolution method based on guided filtering to effectively preserve the spatial information of the image in the network. |
Khwaja Monib Sediqi; Hyo Jong Lee; | arxiv-cs.CV | 2021-03-20 |
| 162 | Bootstrapped Self-Supervised Training with Monocular Video for Semantic Segmentation and Depth Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we leverage temporal consistency between frames in monocular video to perform this bootstrapped self-supervised training. |
Yihao Zhang; John J. Leonard; | arxiv-cs.CV | 2021-03-19 |
| 163 | Video Class Agnostic Segmentation Benchmark for Autonomous Driving Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the open-set segmentation track we evaluate baseline methods that combine appearance, and geometry to learn prototypes per semantic class. |
Mennatullah Siam; Alex Kendall; Martin Jagersand; | arxiv-cs.CV | 2021-03-19 |
| 164 | Improving Image Co-segmentation Via Deep Metric Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel Triplet loss for Image Segmentation, called IS-Triplet loss for short, and combine it with traditional image segmentation loss. |
Zhengwen Li; Xiabi Liu; | arxiv-cs.CV | 2021-03-19 |
| 165 | Investigate Indistinguishable Points in Semantic Segmentation of 3D Point Cloud Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this challenge, we propose a novel Indistinguishable Area Focalization Network (IAF-Net), which selects indistinguishable points adaptively by utilizing the hierarchical semantic features and enhances fine-grained features for points especially those indistinguishable points. |
Mingye Xu; Zhipeng Zhou; Junhao Zhang; Yu Qiao; | arxiv-cs.CV | 2021-03-18 |
| 166 | RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an anchor-free single-stage LiDAR-based 3D object detector — RangeDet. |
Lue Fan; Xuan Xiong; Feng Wang; Naiyan Wang; Zhaoxiang Zhang; | arxiv-cs.CV | 2021-03-18 |
| 167 | 3D Human Pose Estimation with Spatial and Temporal Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present PoseFormer, a purely transformer-based approach for 3D human pose estimation in videos without convolutional architectures involved. |
CE ZHENG et. al. | arxiv-cs.CV | 2021-03-18 |
| 168 | Generic Perceptual Loss for Modeling Structured Output Dependencies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we reveal that, what matters is the network structure instead of the trained weights. |
Yifan Liu; Hao Chen; Yu Chen; Wei Yin; Chunhua Shen; | arxiv-cs.CV | 2021-03-18 |
| 169 | Learning to Recommend Frame for Interactive Video Object Segmentation in The Wild Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a framework for the interactive video object segmentation (VOS) in the wild where users can choose some frames for annotations iteratively. |
ZHAOYUAN YIN et. al. | arxiv-cs.CV | 2021-03-18 |
| 170 | A Location-Sensitive Local Prototype Network for Few-Shot Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Since strong spatial priors exist in many medical imaging modalities, we propose a prototype-based method — namely, the location-sensitive local prototype network — that leverages spatial priors to perform few-shot medical image segmentation. |
Qinji Yu; Kang Dang; Nima Tajbakhsh; Demetri Terzopoulos; Xiaowei Ding; | arxiv-cs.CV | 2021-03-18 |
| 171 | Hierarchical Random Walker Segmentation for Large Volumetric Biomedical Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a hierarchical framework that, to the best of our knowledge, is the first attempt to overcome these restrictions for the random walker algorithm and achieves sublinear run time and constant memory complexity. |
Dominik Drees; Xiaoyi Jiang; | arxiv-cs.CV | 2021-03-17 |
| 172 | Topology-Aware Segmentation Using Discrete Morse Theory Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new approach to train deep image segmentation networks for better topological accuracy. |
Xiaoling Hu; Yusu Wang; Li Fuxin; Dimitris Samaras; Chao Chen; | arxiv-cs.CV | 2021-03-17 |
| 173 | Lite-HDSeg: LiDAR Semantic Segmentation Using Lite Harmonic Dense Convolutions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present Lite-HDSeg, a novel real-time convolutional neural network for semantic segmentation of full $3$D LiDAR point clouds. |
Ryan Razani; Ran Cheng; Ehsan Taghavi; Liu Bingbing; | arxiv-cs.CV | 2021-03-16 |
| 174 | Semi-Supervised Learning for Eye Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents two semi-supervised learning frameworks to identify eye-parts by taking advantage of unlabeled images where labeled datasets are scarce. |
Aayush K. Chaudhary; Prashnna K. Gyawali; Linwei Wang; Jeff B. Pelz; | arxiv-cs.CV | 2021-03-16 |
| 175 | Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: On PASCAL VOC 2012 test images, we achieve mIoUs of 68.0 and 76.9 for weakly and semi-supervised semantic segmentation respectively, which represent a new state-of-the-art. |
Jungbeom Lee; Eunji Kim; Sungroh Yoon; | arxiv-cs.CV | 2021-03-16 |
| 176 | EADNet: Efficient Asymmetric Dilated Network for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an efficient asymmetric dilated semantic segmentation network, named EADNet, which consists of multiple developed asymmetric convolution branches with different dilation rates to capture the variable shapes and scales information of an image. |
QIHANG YANG et. al. | arxiv-cs.CV | 2021-03-16 |
| 177 | Adapt Everywhere: Unsupervised Adaptation of Point-Clouds and Entropy Minimisation for Multi-modal Cardiac Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel UDA method for multi-modal cardiac image segmentation. |
Sulaiman Vesal; Mingxuan Gu; Ronak Kosti; Andreas Maier; Nishant Ravikumar; | arxiv-cs.CV | 2021-03-15 |
| 178 | GSVNet: Guided Spatially-Varying Convolution for Fast Semantic Segmentation on Video Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To leverage fast image segmentation for furthering video segmentation, we propose a simple yet efficient propagation framework. |
Shih-Po Lee; Si-Cun Chen; Wen-Hsiao Peng; | arxiv-cs.CV | 2021-03-15 |
| 179 | Deep Consensus Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes deep consensus learning (DCL) for joint layout-to-image synthesis and weakly-supervised image semantic segmentation. |
Wei Sun; Tianfu Wu; | arxiv-cs.CV | 2021-03-15 |
| 180 | Refine Myself By Teaching Myself: Feature Refinement Via Self-Knowledge Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel self-knowledge distillation method, Feature Refinement via Self-Knowledge Distillation (FRSKD), which utilizes an auxiliary self-teacher network to transfer a refined knowledge for the classifier network. |
Mingi Ji; Seungjae Shin; Seunghyun Hwang; Gibeom Park; Il-Chul Moon; | arxiv-cs.CV | 2021-03-15 |
| 181 | Margin Preserving Self-paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose in this paper a novel margin preserving self-paced contrastive Learning (MPSCL) model for cross-modal medical image segmentation. |
ZHIZHE LIU et. al. | arxiv-cs.CV | 2021-03-15 |
| 182 | S3Net: 3D LiDAR Sparse Semantic Segmentation Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose S3Net, a novel convolutional neural network for LiDAR point cloud semantic segmentation. |
Ran Cheng; Ryan Razani; Yuan Ren; Liu Bingbing; | arxiv-cs.CV | 2021-03-15 |
| 183 | SaNet: Scale-aware Neural Network for Semantic Labelling of Multiple Spatial Resolution Aerial Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel scale-aware neural network (SaNet) for semantic labelling of MSR aerial images to address these two issues. |
LIBO WANG et. al. | arxiv-cs.CV | 2021-03-14 |
| 184 | Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Modular interactive VOS (MiVOS) framework which decouples interaction-to-mask and mask propagation, allowing for higher generalizability and better performance. |
Ho Kei Cheng; Yu-Wing Tai; Chi-Keung Tang; | arxiv-cs.CV | 2021-03-14 |
| 185 | Image Segmentation Methods for Non-destructive Testing Applications Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present new image segmentation methods based on hidden Markov random fields (HMRFs) and cuckoo search (CS) variants. |
EL-Hachemi Guerrout; Ramdane Mahiou; Randa Boukabene; Assia Ouali; | arxiv-cs.CV | 2021-03-13 |
| 186 | Augmented Environment Representations with Complete Object Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a pipeline that can generate a multi-layer representation of indoor environments for robotic applications. |
Krishnananda Prabhu Sivananda; Francesco Verdoja; Ville Kyrki; | arxiv-cs.RO | 2021-03-12 |
| 187 | Thousand to One: Semantic Prior Modeling for Conceptual Coding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a novel end-to-end semantic prior modeling-based conceptual coding scheme towards extremely low bitrate image compression, which leverages semantic-wise deep representations as a unified prior for entropy estimation and texture synthesis. |
JIANHUI CHANG et. al. | arxiv-cs.CV | 2021-03-12 |
| 188 | Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we introduce discriminative region suppression (DRS) module that is a simple yet effective method to expand object activation regions. |
Beomyoung Kim; Sangeun Han; Junmo Kim; | arxiv-cs.CV | 2021-03-12 |
| 189 | Juggling With Representations: On The Information Transfer Between Imagery, Point Clouds, and Meshes for Multi-Modal Semantics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a mesh-centered holistic geometry-driven methodology that explicitly integrates entities of imagery, PC and mesh. |
Dominik Laupheimer; Norbert Haala; | arxiv-cs.CV | 2021-03-12 |
| 190 | Unknown Object Segmentation from Stereo Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, we propose a novel object instance segmentation approach that does not require any semantic or geometric information of the objects beforehand. |
MAXIMILIAN DURNER et. al. | arxiv-cs.CV | 2021-03-11 |
| 191 | Triple-cooperative Video Shadow Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we collect a new video shadow detection dataset, which contains 120 videos with 11, 685 frames, covering 60 object categories, varying lengths, and different motion/lighting conditions. |
ZHIHAO CHEN et. al. | arxiv-cs.CV | 2021-03-11 |
| 192 | Semantic Segmentation for Real Point Cloud Scenes Via Bilateral Augmentation and Adaptive Fusion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we concentrate on the essential visual task, semantic segmentation, for large-scale point cloud data collected in reality. |
Shi Qiu; Saeed Anwar; Nick Barnes; | arxiv-cs.CV | 2021-03-11 |
| 193 | PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To handle these problems, we propose a point-wise affinity propagation module based on the Feature Pyramid Network (FPN) framework, named PointFlow. |
XIANGTAI LI et. al. | arxiv-cs.CV | 2021-03-11 |
| 194 | Learning A Domain-Agnostic Visual Representation for Autonomous Driving Via Contrastive Loss Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Domain-Agnostic Contrastive Learning (DACL) which is a two-stage unsupervised domain adaptation framework with cyclic adversarial training and contrastive loss. |
Dongseok Shim; H. Jin Kim; | arxiv-cs.CV | 2021-03-10 |
| 195 | Continual Semantic Segmentation Via Repulsion-Attraction of Sparse and Disentangled Latent Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we focus on class incremental continual learning in semantic segmentation, where new categories are made available over time while previous training data is not retained. |
Umberto Michieli; Pietro Zanuttigh; | arxiv-cs.CV | 2021-03-10 |
| 196 | Principal Component-based Image Segmentation: A New Approach to Outline in Vitro Cell Colonies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present an objective and versatile machine learning procedure to amend these issues by characterizing, extracting and segmenting inquired colonies using principal component analysis, k-means clustering and a modified watershed segmentation algorithm. |
Delmon Arous; Stefan Schrunner; Ingunn Hanson; Nina F. J. Edin; Eirik Malinen; | arxiv-cs.CV | 2021-03-10 |
| 197 | Evaluating COPY-BLEND Augmentation for Low Level Vision Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we examine the efficacy of a simple copy-blend data augmentation technique that copies patches from noisy images and blends onto a clean image and vice versa to ensure that an underlying algorithm localizes and recovers affected regions resulting in increased perceptual quality of a recovered image. |
Pranjay Shyam; Sandeep Singh Sengar; Kuk-Jin Yoon; Kyung-Soo Kim; | arxiv-cs.CV | 2021-03-10 |
| 198 | FedDG: Federated Domain Generalization on Medical Image Segmentation Via Episodic Learning in Continuous Frequency Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we point out and solve a novel problem setting of federated domain generalization (FedDG), which aims to learn a federated model from multiple distributed source domains such that it can directly generalize to unseen target domains. |
Quande Liu; Cheng Chen; Jing Qin; Qi Dou; Pheng-Ann Heng; | arxiv-cs.CV | 2021-03-10 |
| 199 | Deep Superpixel Cut for Unsupervised Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a deep unsupervised method for image segmentation, which contains the following two stages. |
Qinghong Lin; Weichan Zhong; Jianglin Lu; | arxiv-cs.CV | 2021-03-10 |
| 200 | AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new model, called Attention-Augmented Network (AttaNet), to capture both global context and multilevel semantics while keeping the efficiency high. |
Qi Song; Kangfu Mei; Rui Huang; | arxiv-cs.CV | 2021-03-10 |
| 201 | Pixel-wise Anomaly Detection in Complex Driving Scenes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we demonstrate that these two methodologies contain complementary information and can be combined to produce robust predictions for anomaly segmentation. |
Giancarlo Di Biase; Hermann Blum; Roland Siegwart; Cesar Cadena; | arxiv-cs.CV | 2021-03-09 |
| 202 | Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim at seeking for a more accurate learning-based class-agnostic pseudo mask generator tailored to box-supervised semantic segmentation. |
CHAOHAO XIE et. al. | arxiv-cs.CV | 2021-03-09 |
| 203 | Deep Learning Based 3D Segmentation: A Survey Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper provides a comprehensive survey of recent progress in deep learning based 3D segmentation covering over 150 papers. |
YONG HE et. al. | arxiv-cs.CV | 2021-03-09 |
| 204 | ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a challenging dataset, ChangeSim, aimed at online scene change detection (SCD) and more. |
JIN-MAN PARK et. al. | arxiv-cs.CV | 2021-03-09 |
| 205 | Point-supervised Segmentation of Microscopy Images and Volumes Via Objectness Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our approach has two key aspects: (1) we construct a graph-theoretic soft-segmentation using individual seeds to be used within a regularizer during training and (2) we use an objective function that enables learning from the constructed soft-labels. |
SHIJIE LI et. al. | arxiv-cs.CV | 2021-03-09 |
| 206 | MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this issue, we advance a MetaCorrection framework, where a Domain-aware Meta-learning strategy is devised to benefit Loss Correction (DMLC) for UDA semantic segmentation. |
Xiaoqing Guo; Chen Yang; Baopu Li; Yixuan Yuan; | arxiv-cs.CV | 2021-03-09 |
| 207 | Capturing Omni-Range Context for Omnidirectional Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To bridge the gap in terms of FoV and structural distribution between the imaging domains, we introduce Efficient Concurrent Attention Networks (ECANets), directly capturing the inherent long-range dependencies in omnidirectional imagery. |
Kailun Yang; Jiaming Zhang; Simon Reiß; Xinxin Hu; Rainer Stiefelhagen; | arxiv-cs.CV | 2021-03-09 |
| 208 | Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By formulating joint association as maximum-weight bipartite matching, a differentiable solution is developed to exploit projected gradient descent and Dykstra’s cyclic projection algorithm. |
Tianfei Zhou; Wenguan Wang; Si Liu; Yi Yang; Luc Van Gool; | arxiv-cs.CV | 2021-03-08 |
| 209 | Dual-Task Mutual Learning for Semi-Supervised Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel dual-task mutual learning framework for semi-supervised medical image segmentation. |
Yichi Zhang; Jicong Zhang; | arxiv-cs.CV | 2021-03-08 |
| 210 | Semi-supervised Domain Adaptation Based on Dual-level Domain Mixing for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We focus on a more practical setting of semi-supervised domain adaptation (SSDA) where both a small set of labeled target data and large amounts of labeled source data are available. |
Shuaijun Chen; Xu Jia; Jianzhong He; Yongjie Shi; Jianzhuang Liu; | arxiv-cs.CV | 2021-03-08 |
| 211 | Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel multi-source domain adaptation framework based on collaborative learning for semantic segmentation. |
Jianzhong He; Xu Jia; Shuaijun Chen; Jianzhuang Liu; | arxiv-cs.CV | 2021-03-08 |
| 212 | Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel semi-supervised segmentation method that leverages mutual information (MI) on categorical distributions to achieve both global representation invariance and local smoothness. |
Jizong Peng; Marco Pedersoli; Christian Desrosiers; | arxiv-cs.CV | 2021-03-08 |
| 213 | TransBTS: Multimodal Brain Tumor Segmentation Using Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we for the first time exploit Transformer in 3D CNN for MRI Brain Tumor Segmentation and propose a novel network named TransBTS based on the encoder-decoder structure. |
WENXUAN WANG et. al. | arxiv-cs.CV | 2021-03-07 |
| 214 | Panoptic Lintention Network: Towards Efficient Navigational Perception for The Visually Impaired Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we utilize panoptic segmentation to assist the navigation of visually impaired people by offering both things and stuff awareness in the proximity of the visually impaired efficiently. |
Wei Mao; Jiaming Zhang; Kailun Yang; Rainer Stiefelhagen; | arxiv-cs.CV | 2021-03-06 |
| 215 | Learning Statistical Texture for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we fully take advantages of the low-level texture features and propose a novel Statistical Texture Learning Network (STLNet) for semantic segmentation. |
LANYUN ZHU et. al. | arxiv-cs.CV | 2021-03-06 |
| 216 | Perception Framework Through Real-Time Semantic Segmentation and Scene Recognition on A Wearable System for The Visually Impaired Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As the scene information, including objectness and scene type, are important for people with visual impairment, in this work we present a multi-task efficient perception system for the scene parsing and recognition tasks. |
Yingzhi Zhang; Haoye Chen; Kailun Yang; Jiaming Zhang; Rainer Stiefelhagen; | arxiv-cs.CV | 2021-03-06 |
| 217 | High-Resolution Segmentation of Tooth Root Fuzzy Edge Based on Polynomial Curve Fitting with Landmark Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a model for high-resolution segmentation based on polynomial curve fitting with landmark detection (HS-PCL). |
YUNXIANG LI et. al. | arxiv-cs.CV | 2021-03-06 |
| 218 | Hidden Backdoor Attack Against Semantic Segmentation Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we reveal that this threat could also happen in semantic segmentation, which may further endanger many mission-critical applications ($e.g.$, autonomous driving). |
Yiming Li; Yanjie Li; Yalei Lv; Yong Jiang; Shu-Tao Xia; | arxiv-cs.CR | 2021-03-06 |
| 219 | Fine-Grained Off-Road Semantic Segmentation and Mapping Via Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This research proposes a contrastive learning based method. |
Biao Gao; Shaochi Hu; Xijun Zhao; Huijing Zhao; | arxiv-cs.CV | 2021-03-05 |
| 220 | Fast Interactive Video Object Segmentation with Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present a graph neural network based approach for tackling the problem of interactive video object segmentation. |
Viktor Varga; András Lőrincz; | arxiv-cs.CV | 2021-03-05 |
| 221 | Deeply Supervised UNet for Semantic Segmentation to Assist Dermatopathological Assessment of Basal Cell Carcinoma (BCC) Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we successfully develop a deep learning method to assist the pathologists by marking critical regions that have a high probability of exhibiting pathological features in Whole Slide Images (WSI). |
JEAN LE’CLERC ARRASTIA et. al. | arxiv-cs.LG | 2021-03-05 |
| 222 | NeRD: Neural Representation of Distribution for Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Using NeRD, we propose an end-to-end deep learning model for medical image segmentation that can compensate the negative impact of feature distribution shifting issue caused by commonly used network operations such as padding and pooling. |
HANG ZHANG et. al. | arxiv-cs.CV | 2021-03-05 |
| 223 | Morphological Operation Residual Blocks: Enhancing 3D Morphological Feature Representation in Convolutional Neural Networks for Semantic Segmentation of Medical Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we introduced a 3D morphological operation residual block to extract morphological features in end-to-end deep learning models for semantic segmentation. |
Chentian Li; Chi Ma; William W. Lu; | arxiv-cs.CV | 2021-03-05 |
| 224 | Learning Whole-Slide Segmentation from Inexact and Incomplete Labels Using Tissue Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose SegGini, a weakly supervised segmentation method using graphs, that can utilize weak multiplex annotations, i.e. inexact and incomplete annotations, to segment arbitrary and large images, scaling from tissue microarray (TMA) to whole slide image (WSI). |
VALENTIN ANKLIN et. al. | arxiv-cs.CV | 2021-03-04 |
| 225 | Implicit Integration of Superpixel Segmentation Into Fully Convolutional Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a way to implicitly integrate a superpixel scheme into CNNs, which makes it easy to use superpixels with CNNs in an end-to-end fashion. |
Teppei Suzuki; | arxiv-cs.CV | 2021-03-04 |
| 226 | CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel framework that efficiently bridges a {\bf Co}nvolutional neural network and a {\bf Tr}ansformer {\bf (CoTr)} for accurate 3D medical image segmentation. |
Yutong Xie; Jianpeng Zhang; Chunhua Shen; Yong Xia; | arxiv-cs.CV | 2021-03-04 |
| 227 | Semi-supervised Left Atrium Segmentation with Mutual Consistency Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, in this paper, we propose a novel Mutual Consistency Network (MC-Net) for semi-supervised left atrium segmentation from 3D MR images. |
Yicheng Wu; Minfeng Xu; Zongyuan Ge; Jianfei Cai; Lei Zhang; | arxiv-cs.CV | 2021-03-04 |
| 228 | LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We therefore propose a recurrent segmentation architecture (RNN), which takes a single range image frame as input and exploits recursively aggregated temporal information. |
Fabian Duerr; Mario Pfaller; Hendrik Weigel; Juergen Beyerer; | arxiv-cs.CV | 2021-03-03 |
| 229 | K-means Segmentation Based-on Lab Color Space for Embryo Egg Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This study aims to detect the presence of embryos in eggs. |
Shoffan Saifullah; | arxiv-cs.CV | 2021-03-03 |
| 230 | Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Recently, many semantic segmentation approaches based on convolutional neural networks (CNNs) have been proposed for pixel-wise drivable area and road anomaly detection. Therefore, in this paper, we first build a drivable area and road anomaly detection benchmark for ground mobile robots, evaluating the existing state-of-the-art single-modal and data-fusion semantic segmentation CNNs using six modalities of visual features. |
Hengli Wang; Rui Fan; Yuxiang Sun; Ming Liu; | arxiv-cs.CV | 2021-03-03 |
| 231 | Cross-View Regularization for Domain Adaptive Panoptic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We design a domain adaptive panoptic segmentation network that exploits inter-style consistency and inter-task regularization for optimal domain adaptive panoptic segmentation. |
Jiaxing Huang; Dayan Guan; Aoran Xiao; Shijian Lu; | arxiv-cs.CV | 2021-03-03 |
| 232 | Unsupervised Domain Adaptation Network with Category-Centric Prototype Aligner for Biomedical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this problem, we present a novel unsupervised domain adaptation network, for generalizing models learned from the labeled source domain to the unlabeled target domain for cross-modality biomedical image segmentation. |
Ping Gong; Wenwen Yu; Qiuwen Sun; Ruohan Zhao; Junfeng Hu; | arxiv-cs.CV | 2021-03-03 |
| 233 | Uncertainty Guided Semi-supervised Segmentation of Retinal Layers in OCT Images IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel uncertainty-guided semi-supervised learning based on a student-teacher approach for training the segmentation network using limited labeled samples and a large number of unlabeled images. |
SUMAN SEDAI et. al. | arxiv-cs.CV | 2021-03-02 |
| 234 | PECNet: A Deep Multi-Label Segmentation Network for Eosinophilic Esophagitis Biopsy Diagnostics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Herein, we aimed to use machine learning to identify, quantitate and diagnose EoE. |
NATI DANIEL et. al. | arxiv-cs.CV | 2021-03-02 |
| 235 | HED-UNet: Combined Segmentation and Edge Detection for Monitoring The Antarctic Coastline Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To take into account this task duality, we therefore devise a new model to unite these two approaches in a deep learning model. |
Konrad Heidler; Lichao Mou; Celia Baumhoer; Andreas Dietz; Xiao Xiang Zhu; | arxiv-cs.CV | 2021-03-02 |
| 236 | Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we present a Context Decoupling Augmentation (CDA) method, to change the inherent context in which the objects appear and thus drive the network to remove the dependence between object instances and contextual information. |
Yukun Su; Ruizhou Sun; Guosheng Lin; Qingyao Wu; | arxiv-cs.CV | 2021-03-02 |
| 237 | Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a systematic and up-to-date review of the solutions above, with summaries and comments about the methodologies. |
Jialin Peng; Ye Wang; | arxiv-cs.CV | 2021-02-28 |
| 238 | Snowy Night-to-Day Translator and Semantic Segmentation Label Similarity for Snow Hazard Indicator Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper propose a method to automate a snow hazard indicator that the road surface region is generated from the night snow image using the Conditional GAN, pix2pix. |
Takato Yasuno; Hiroaki Sugawara; Junichiro Fujii; Ryuto Yoshida; | arxiv-cs.CV | 2021-02-28 |
| 239 | FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We design FPS-Net, a convolutional fusion network that exploits the uniqueness and discrepancy among the projected image channels for optimal point cloud segmentation. |
Aoran Xiao; Xiaofei Yang; Shijian Lu; Dayan Guan; Jiaxing Huang; | arxiv-cs.CV | 2021-02-28 |
| 240 | Achieving Competitive Play Through Bottom-Up Approach in Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that strong performance can still be achieved using a bottom-up approach for vision-based object recognition tasks and achieve competitive video game play. |
E. Pryzant; Q. Deng; B. Mei; E. Shrestha; | arxiv-cs.CV | 2021-02-28 |
| 241 | SUM: A Benchmark Dataset of Semantic Urban Meshes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a new benchmark dataset of semantic urban meshes, a novel semi-automatic annotation framework, and an open-source annotation tool for 3D meshes. |
Weixiao Gao; Liangliang Nan; Bas Boom; Hugo Ledoux; | arxiv-cs.CV | 2021-02-27 |
| 242 | Exposing Semantic Segmentation Failures Via Maximum Discrepancy Competition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we take steps toward answering the question by exposing failures of existing semantic segmentation methods in the open visual world under the constraint of very limited human labeling effort. |
Jiebin Yan; Yu Zhong; Yuming Fang; Zhangyang Wang; Kede Ma; | arxiv-cs.CV | 2021-02-27 |
| 243 | A Novel Adaptive Deep Network for Building Footprint Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the current paper, we propose a novel network-based on Pix2Pix methodology to solve the problem of inaccurate boundaries obtained by converting satellite images into maps using segmentation networks in order to segment building footprints. |
A. Ziaee; R. Dehbozorgi; M. Döller; | arxiv-cs.CV | 2021-02-27 |
| 244 | Recursive Training for Zero-Shot Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a recursive training scheme to supervise the retraining of a semantic segmentation model for a zero-shot setting using a pseudo-feature representation. |
Ce Wang; Moshiur Farazi; Nick Barnes; | arxiv-cs.CV | 2021-02-26 |
| 245 | MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address this point by proposing to search for generalizable U-shape architectures on a composited dataset that mixes medical images from multiple segmentation tasks and domains creatively, which is named MixSearch. |
LUYAN LIU et. al. | arxiv-cs.CV | 2021-02-25 |
| 246 | A Reconfigurable Winograd CNN Accelerator with Nesting Decomposition Algorithm for Computing Convolution with Large Filters Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes a nested Winograd algorithm to iteratively decompose a large filter into a sequence of 3×3 tiles which can then be accelerated with a 3×3 Winograd algorithm. |
Jingbo Jiang; Xizi Chen; Chi-Ying Tsui; | arxiv-cs.CV | 2021-02-25 |
| 247 | Multi-Domain Learning By Meta-Learning: Taking Optimal Steps in Multi-Domain Loss Landscapes By Inner-Loop Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, given emerging multi-modal data (e.g., various structural neuroimaging modalities), we aim to enable MDL purely algorithmically so that widely used neural networks can trivially achieve MDL in a model-independent manner. |
ANTHONY SICILIA et. al. | arxiv-cs.CV | 2021-02-25 |
| 248 | Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel method that tackles the problem of unsupervised domain adaptation for semantic segmentation by maximizing the cosine similarity between the source and the target domain at the feature level. |
Inseop Chung; Daesik Kim; Nojun Kwak; | arxiv-cs.CV | 2021-02-25 |
| 249 | Synergy Between Semantic Segmentation and Image Denoising Via Alternate Boosting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, we are interested in the synergy between them by using a holistic deep model. |
Shunxin Xu; Ke Sun; Dong Liu; Zhiwei Xiong; Zheng-Jun Zha; | arxiv-cs.CV | 2021-02-24 |
| 250 | Image Augmentation for Multitask Few-Shot Learning: Agricultural Domain Use-Case Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce an image augmentation framework, which enables us to extremely enlarge the number of training samples while providing the data for such tasks as object detection, semantic segmentation, instance segmentation, object counting, image denoising, and classification. |
Sergey Nesteruk; Dmitrii Shadrin; Mariia Pukalchik; | arxiv-cs.CV | 2021-02-24 |
| 251 | Direct Estimation of Appearance Models for Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We describe a novel approach for estimating appearance models directly from an image, without explicit consideration of the pixels that make up each region. |
Jeova F. S. Rocha Neto; Pedro Felzenszwalb; Marilyn Vazquez; | arxiv-cs.CV | 2021-02-22 |
| 252 | Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to leverage the multi-class label information during the episodic training. |
TAO CHEN et. al. | arxiv-cs.CV | 2021-02-22 |
| 253 | Medical Transformer: Gated Axial-Attention for Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a Gated Axial-Attention model which extends the existing architectures by introducing an additional control mechanism in the self-attention module. |
Jeya Maria Jose Valanarasu; Poojan Oza; Ilker Hacihaliloglu; Vishal M. Patel; | arxiv-cs.CV | 2021-02-21 |
| 254 | Improved Semantic Segmentation of Tuberculosis-consistent Findings in Chest X-rays Using Augmented Training of Modality-specific U-Net Models with Weak Localizations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we train chest X-ray (CXR) modality-specific U-Nets and other state-of-the-art U-Net models for semantic segmentation of tuberculosis (TB)-consistent findings. |
Sivaramakrishnan Rajaraman; Les Folio; Jane Dimperio; Philip Alderson; Sameer Antani; | arxiv-cs.CV | 2021-02-21 |
| 255 | Analyzing Overfitting Under Class Imbalance in Neural Networks for Image Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we provide new insights on the problem of overfitting under class imbalance by inspecting the network behavior. |
Zeju Li; Konstantinos Kamnitsas; Ben Glocker; | arxiv-cs.CV | 2021-02-20 |
| 256 | EMDS-5: Environmental Microorganism Image Dataset Fifth Version for Multiple Image Analysis Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Six methods are used for single-object image segmentation, while k-means and U-net are used for multi-object segmentation.We extract nine features from the images in EMDS-5 and use the Support Vector Machine classifier for testing. |
ZIHAN LI et. al. | arxiv-cs.CV | 2021-02-20 |
| 257 | CheXseg: Combining Expert Annotations with DNN-generated Saliency Maps for X-ray Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a method that combines the high quality of pixel-level expert annotations with the scale of coarse DNN-generated saliency maps for training multi-label semantic segmentation models. |
Soham Gadgil; Mark Endo; Emily Wen; Andrew Y. Ng; Pranav Rajpurkar; | arxiv-cs.CV | 2021-02-20 |
| 258 | Adaptable Deformable Convolutions for Semantic Segmentation of Fisheye Images in Autonomous Driving Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work demonstrates that a CNN trained on standard images can be readily adapted to fisheye images, which is crucial in real-world applications where time-consuming real-time data transformation must be avoided. |
Clément Playout; Ola Ahmad; Freddy Lecue; Farida Cheriet; | arxiv-cs.CV | 2021-02-19 |
| 259 | Scribble-Supervised Semantic Segmentation By Uncertainty Reduction on Neural Representation and Self-Supervision on Neural Eigenspace Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we propose holistic operations, including minimizing entropy and a network embedded random walk on neural representation to reduce uncertainty. |
Zhiyi Pan; Peng Jiang; Yunhai Wang; Changhe Tu; Anthony G. Cohn; | arxiv-cs.CV | 2021-02-19 |
| 260 | Image Compositing for Segmentation of Surgical Tools Without Manual Annotations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We compare different methods to blend instruments over tissue and propose a novel data augmentation approach that takes advantage of the plurality of options. |
LUIS C. GARCIA-PERAZA-HERRERA et. al. | arxiv-cs.CV | 2021-02-18 |
| 261 | Benefits of Linear Conditioning with Metadata for Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we adapt a linear conditioning method called FiLM (Feature-wise Linear Modulation) for image segmentation tasks. |
ANDREANNE LEMAY et. al. | arxiv-cs.CV | 2021-02-18 |
| 262 | Temporal Memory Attention for Video Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Temporal Memory Attention Network (TMANet) to adaptively integrate the long-range temporal relations over the video sequence based on the self-attention mechanism without exhaustive optical flow prediction. |
Hao Wang; Weining Wang; Jing Liu; | arxiv-cs.CV | 2021-02-17 |
| 263 | TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the more challenging problem of improving efficiency in modeling global contexts without losing localization ability for low-level details. |
Yundong Zhang; Huiye Liu; Qiang Hu; | arxiv-cs.CV | 2021-02-16 |
| 264 | Uncertainty-based Method for Improving Poorly Labeled Segmentation Datasets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a framework to train binary segmentation DCNNs using sets of unreliable pixel-level annotations. |
Ekaterina Redekop; Alexey Chernyavskiy; | arxiv-cs.CV | 2021-02-16 |
| 265 | Feature Pyramid Network with Multi-Head Attention for Semantic Segmentation of Fine-Resolution Remotely Sensed Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, in this paper, we introduce the Feature Pyramid Net-work (FPN) to bridge the gap between the low-level and high-level features. |
Rui Li; Shunyi Zheng; Chenxi Duan; | arxiv-cs.CV | 2021-02-16 |
| 266 | Reconstruction-Based Membership Inference Attacks Are Easier on Difficult Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this, we propose using a novel predictability score that can be computed for each sample, and its computation does not require a training set. |
Avital Shafran; Shmuel Peleg; Yedid Hoshen; | arxiv-cs.LG | 2021-02-15 |
| 267 | OmniDet: Surround View Cameras Based Multi-task Visual Perception Network for Autonomous Driving Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents a multi-task visual perception network on unrectified fisheye images to enable the vehicle to sense its surrounding environment. |
VARUN RAVI KUMAR et. al. | arxiv-cs.CV | 2021-02-15 |
| 268 | Segmenting Two-dimensional Structures with Strided Tensor Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel formulation of tensor networks for supervised image segmentation which allows them to operate on high resolution medical images. |
Raghavendra Selvan; Erik B Dam; Jens Petersen; | arxiv-cs.CV | 2021-02-13 |
| 269 | Fast, Accurate Barcode Detection in Ultra High-Resolution Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose using semantic segmentation to achieve a fast and accurate detection of barcodes of various scales in UHR images. |
Jerome Quenum; Kehan Wang; Avideh Zakhor; | arxiv-cs.CV | 2021-02-13 |
| 270 | Saliency-Aware Class-Agnostic Food Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose a class-agnostic food image segmentation method. |
SRI KALYAN YARLAGADDA et. al. | arxiv-cs.CV | 2021-02-13 |
| 271 | Multi-source Pseudo-label Learning of Semantic Segmentation for The Scene Recognition of Agricultural Mobile Robots Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes a novel method of training a semantic segmentation model for environment recognition of agricultural mobile robots by unsupervised domain adaptation exploiting publicly available datasets of outdoor scenes that are different from our target environments i.e., greenhouses. |
Shigemichi Matsuzaki; Jun Miura; Hiroaki Masuzawa; | arxiv-cs.CV | 2021-02-12 |
| 272 | INSTA-YOLO: Real-Time Instance Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Insta-YOLO, a novel one-stage end-to-end deep learning model for real-time instance segmentation. |
Eslam Mohamed; Abdelrahman Shaker; Hazem Rashed; Ahmad El-Sallab; Mayada Hadhoud; | arxiv-cs.CV | 2021-02-12 |
| 273 | Adversarial Segmentation Loss for Sketch Colorization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new method for generating color images from sketches or edge maps. |
Samet Hicsonmez; Nermin Samet; Emre Akbas; Pinar Duygulu; | arxiv-cs.CV | 2021-02-11 |
| 274 | Unsupervised Semantic Segmentation By Contrasting Object Mask Proposals Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we make a first attempt to tackle the problem on datasets that have been traditionally utilized for the supervised case. |
Wouter Van Gansbeke; Simon Vandenhende; Stamatios Georgoulis; Luc Van Gool; | arxiv-cs.CV | 2021-02-11 |
| 275 | L-SNet: from Region Localization to Scale Invariant Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a differentiable two-stage network architecture to tackle these problems. |
Jiahao Xie; Sheng Zhang; Jianwei Lu; Ye Luo; | arxiv-cs.CV | 2021-02-11 |
| 276 | The Hessigheim 3D (H3D) Benchmark on Semantic Segmentation of High-Resolution 3D Point Clouds and Textured Meshes from UAV LiDAR and Multi-View-Stereo Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Within this paper, we aim to alleviate this issue by introducing a new annotated 3D dataset that is unique in three ways: i) The dataset consists of both an Unmanned Aerial Vehicle (UAV) laser scanning point cloud and a 3D textured mesh. |
MICHAEL KÖLLE et. al. | arxiv-cs.CV | 2021-02-10 |
| 277 | TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose TransUNet, which merits both Transformers and U-Net, as a strong alternative for medical image segmentation. |
JIENENG CHEN et. al. | arxiv-cs.CV | 2021-02-08 |
| 278 | Semantic Segmentation with Labeling Uncertainty and Class Imbalance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As such, we present a new approach that calculates a weight for each pixel considering its class and uncertainty during the labeling process. |
PATRIK OLÃ BRESSAN et. al. | arxiv-cs.CV | 2021-02-08 |
| 279 | (AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this problem, we propose AF2-S3Net, an end-to-end encoder-decoder CNN network for 3D LiDAR semantic segmentation. |
Ran Cheng; Ryan Razani; Ehsan Taghavi; Enxu Li; Bingbing Liu; | arxiv-cs.CV | 2021-02-08 |
| 280 | SwiftNet: Real-time Video Object Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we present SwiftNet for real-time semisupervised video object segmentation (one-shot VOS), which reports 77.8% J &F and 70 FPS on DAVIS 2017 validation dataset, leading all present solutions in overall accuracy and speed performance. |
Haochen Wang; Xiaolong Jiang; Haibing Ren; Yao Hu; Song Bai; | arxiv-cs.CV | 2021-02-08 |
| 281 | MudrockNet: Semantic Segmentation of Mudrock SEM Images Through Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose a deep learning SEM image segmentation model, MudrockNet based on Google’s DeepLab-v3+ architecture implemented with the TensorFlow library. |
ABHISHEK BIHANI et. al. | arxiv-cs.CV | 2021-02-05 |
| 282 | Bidirectional Multi-scale Attention Networks for Semantic Segmentation of Oblique UAV Imagery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to tackle the scale variation issue, in this paper, we propose the novel bidirectional multi-scale attention networks, which fuse features from multiple scales bidirectionally for more adaptive and effective feature extraction. |
Ye Lyu; George Vosselman; Gui-Song Xia; Michael Ying Yang; | arxiv-cs.CV | 2021-02-05 |
| 283 | Active Boundary Loss for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel active boundary loss for semantic segmentation. |
CHI WANG et. al. | arxiv-cs.CV | 2021-02-04 |
| 284 | ABCNet: Attentive Bilateral Contextual Network for Efficient Semantic Segmentation of Fine-Resolution Remote Sensing Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an Attentive Bilateral Contextual Network (ABCNet), a convolutional neural network (CNN) with double branches, with prominently lower computational consumptions compared to the cutting-edge algorithms, while maintaining a competitive accuracy. |
Rui Li; Chenxi Duan; | arxiv-cs.CV | 2021-02-04 |
| 285 | Learning to Segment Human Body Parts with Synthetically Trained Deep Convolutional Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a new framework for human body part segmentation based on Deep Convolutional Neural Networks trained using only synthetic data. |
ALESSANDRO SAVIOLO et. al. | arxiv-cs.CV | 2021-02-02 |
| 286 | Co-Seg: An Image Segmentation Framework Against Label Corruption Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel deep learning framework, namely Co-Seg, to collaboratively train segmentation networks on datasets which include low-quality noisy labels. |
ZIYI HUANG et. al. | arxiv-cs.LG | 2021-01-31 |
| 287 | ObjectAug: Object-level Data Augmentation for Semantic Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose ObjectAug to perform object-level augmentation for semantic image segmentation. |
Jiawei Zhang; Yanchun Zhang; Xiaowei Xu; | arxiv-cs.CV | 2021-01-30 |
| 288 | Deep Learning–Based Scene Simplification for Bionic Vision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we combine deep learning–based scene simplification strategies with a psychophysically validated computational model of the retina to generate realistic predictions of simulated prosthetic vision, and measure their ability to support scene understanding of sighted subjects (virtual patients) in a variety of outdoor scenarios. |
Nicole Han; Sudhanshu Srivastava; Aiwen Xu; Devi Klein; Michael Beyeler; | arxiv-cs.CV | 2021-01-30 |
| 289 | Neural Networks for Semantic Segmentation of Historical City Maps: Cross-cultural Performance and The Impact of Figurative Diversity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a new semantic segmentation model for historical city maps that surpasses the state of the art in terms of flexibility and performance. |
Rémi Petitpierre; | arxiv-cs.CV | 2021-01-29 |
| 290 | DRIV100: In-The-Wild Multi-Domain Dataset and Evaluation for Real-World Domain Adaptation of Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Together with the recent advances in semantic segmentation, many domain adaptation methods have been proposed to overcome the domain gap between training and deployment environments. |
Haruya Sakashita; Christoph Flothow; Noriko Takemura; Yusuke Sugano; | arxiv-cs.CV | 2021-01-29 |
| 291 | Exploring Cross-Image Pixel Contrast for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the recent advance in unsupervised contrastive representation learning, we propose a pixel-wise contrastive framework for semantic segmentation in the fully supervised setting. |
WENGUAN WANG et. al. | arxiv-cs.CV | 2021-01-28 |
| 292 | Utilizing Uncertainty Estimation in Deep Learning Segmentation of Fluorescence Microscopy Images with Missing Markers IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We herein propose a method to estimate segmentation quality on unlabeled images by (i) estimating both aleatoric and epistemic uncertainties of convolutional neural networks for image segmentation, and (ii) training a Random Forest model for the interpretation of uncertainty features via regression to their corresponding segmentation metrics. |
Alvaro Gomariz; Raphael Egli; Tiziano Portenier; César Nombela-Arrieta; Orcun Goksel; | arxiv-cs.CV | 2021-01-27 |
| 293 | Effects of Image Size on Deep Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Image interpolation algorithms are used to double the cropped image size and create new datasets. |
Olivier Rukundo; | arxiv-cs.CV | 2021-01-27 |
| 294 | Puzzle-CAM: Improved Localization Via Matching Partial and Full Features IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose Puzzle-CAM, a process that minimizes differences between the features from separate patches and the whole image. |
Sanghyun Jo; In-Jae Yu; | arxiv-cs.CV | 2021-01-27 |
| 295 | Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we rely on representative prototypes, the feature centroids of classes, to address the two issues for unsupervised domain adaptation. |
PAN ZHANG et. al. | arxiv-cs.CV | 2021-01-26 |
| 296 | Global-Local Propagation Network for RGB-D Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Global-Local propagation network (GLPNet) to solve this problem. |
Sihan Chen; Xinxin Zhu; Wei Liu; Xingjian He; Jing Liu; | arxiv-cs.CV | 2021-01-26 |
| 297 | Joint Forecasting of Features and Feature Motion for Dense Semantic Future Prediction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel dense semantic forecasting approach which is applicable to a variety of architectures and tasks. |
Josip Šarić; Sacha Vražić; Siniša Šegvić; | arxiv-cs.CV | 2021-01-26 |
| 298 | Mask-based Data Augmentation for Semi-supervised Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose a new approach for data augmentation, termed ComplexMix, which incorporates aspects of CutMix and ClassMix with improved performance. |
Ying Chen; Xu Ouyang; Kaiyue Zhu; Gady Agam; | arxiv-cs.CV | 2021-01-25 |
| 299 | Anchor Distance for 3D Multi-Object Distance Estimation from 2D Single Shot IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a real time approach for estimating the distances to multiple objects in a scene using only a single-shot image. |
Hyeonwoo Yu; Jean Oh; | arxiv-cs.CV | 2021-01-25 |
| 300 | OpenGF: An Ultra-Large-Scale Ground Filtering Dataset Built Upon Open ALS Point Clouds Around The World IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we present OpenGF, first Ultra-Large-Scale Ground Filtering dataset covering over 47 $km^2$ of 9 different typical terrain scenes built upon open ALS point clouds of 4 different countries around the world. |
Nannan Qin; Weikai Tan; Lingfei Ma; Dedong Zhang; Jonathan Li; | arxiv-cs.CV | 2021-01-23 |
| 301 | Network-Agnostic Knowledge Transfer for Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a knowledge transfer approach from a teacher to a student network wherein we train the student on an independent transferal dataset, whose annotations are generated by the teacher. |
SHUHANG WANG et. al. | arxiv-cs.CV | 2021-01-23 |
| 302 | Vessel-CAPTCHA: An Efficient Learning Framework for Vessel Annotation and Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these problems, we propose a novel annotation-efficient deep learning vessel segmentation framework. |
VIEN NGOC DANG et. al. | arxiv-cs.CV | 2021-01-22 |
| 303 | DSAL: Deeply Supervised Active Learning from Strong and Weak Labelers for Biomedical Image Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a deep active semi-supervised learning framework, DSAL, combining active learning and semi-supervised learning strategies. |
Ziyuan Zhao; Zeng Zeng; Kaixin Xu; Cen Chen; Cuntai Guan; | arxiv-cs.CV | 2021-01-22 |
| 304 | Personal Fixations-Based Object Segmentation with Object Localization and Boundary Preservation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on Personal Fixations-based Object Segmentation (PFOS) to address issues in previous studies, such as the lack of appropriate dataset and the ambiguity in fixations-based interaction. In particular, we first construct a new PFOS dataset by carefully collecting pixel-level binary annotation data over an existing fixation prediction dataset, such dataset is expected to greatly facilitate the study along the line. |
GONGYANG LI et. al. | arxiv-cs.CV | 2021-01-22 |
| 305 | SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we introduce a Transformer-based approach to video object segmentation (VOS). |
Brendan Duke; Abdalla Ahmed; Christian Wolf; Parham Aarabi; Graham W. Taylor; | arxiv-cs.CV | 2021-01-21 |
| 306 | CO2: Consistent Contrast for Unsupervised Visual Representation Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a consistency regularization term into the current contrastive learning framework. |
Chen Wei; Huiyu Wang; Wei Shen; Alan Yuille; | iclr | 2021-01-21 |
| 307 | MPASNET: Motion Prior-Aware Siamese Network for Unsupervised Deep Crowd Segmentation in Video Scenes IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the Motion Prior-Aware Siamese Network (MPASNET) for unsupervised crowd semantic segmentation. |
Jinhai Yang; Hua Yang; | arxiv-cs.CV | 2021-01-21 |
| 308 | Segmenting Transparent Object in The Wild with Transformer IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents a new fine-grained transparent object segmentation dataset, termed Trans10K-v2, extending Trans10K-v1, the first large-scale transparent object segmentation dataset. |
ENZE XIE et. al. | arxiv-cs.CV | 2021-01-21 |
| 309 | Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Auto Seg-Loss is the first general framework for searching surrogate losses for mainstream semantic segmentation metrics. |
HAO LI et. al. | iclr | 2021-01-21 |
| 310 | You Only Need Adversarial Supervision for Semantic Image Synthesis IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose OASIS, a novel model for multi-modal semantic image synthesis, improving over previous methods in terms of image quality and diversity while only using adversarial supervision. |
EDGAR SCH�NFELD et. al. | iclr | 2021-01-21 |
| 311 | Cut Out The Annotator, Keep The Cutout: Better Segmentation with Weak Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a weak supervision approach for segmentation tasks, allowing users to train high-performing segmentation CNNs with very few hand-labeled training points. |
SARAH HOOPER et. al. | iclr | 2021-01-21 |
| 312 | Finger Vein Recognition By Generating Code IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tack these problems, this paper proposes a new finger vein recognition by generating code. |
Zhongxia Zhang; Mingwen Wang; | arxiv-cs.CV | 2021-01-20 |
| 313 | Rethinking Semantic Segmentation Evaluation for Explainability and Model Selection IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we introduce a new metric to assess region-based over- and under-segmentation. |
Yuxiang Zhang; Sachin Mehta; Anat Caspi; | arxiv-cs.CV | 2021-01-20 |
| 314 | Nonparametric Clustering for Image Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Pixel similarity is evaluated in terms of density of the color representation and the adjacency structure of the pixels is exploited to introduce a simple, yet effective method to identify image segments as disconnected high-density regions. |
Giovanna Menardi; | arxiv-cs.CV | 2021-01-20 |
| 315 | Feature Sharing Cooperative Network for Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By inspired from human learning method, we propose a semantic segmentation method using cooperative learning which shares the information resembling a group learning. |
Ryota Ikedo; Kazuhiro Hotta; | arxiv-cs.CV | 2021-01-19 |
| 316 | Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our final contribution shows how to use a DSG for real-time hierarchical semantic path-planning. |
ANTONI ROSINOL et. al. | arxiv-cs.RO | 2021-01-18 |
| 317 | Channelized Axial Attention for Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we proposethe Channelized Axial Attention (CAA) to seamlessly integratechannel attention and axial attention with reduced computationalcomplexity. |
YE HUANG et. al. | arxiv-cs.CV | 2021-01-18 |
| 318 | Soft Constrained Autonomous Vehicle Navigation Using Gaussian Processes and Instance Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a generic feature-based navigation framework for autonomous vehicles using a soft constrained Particle Filter. |
Bruno H. Groenner Barbosa; Neel P. Bhatt; Amir Khajepour; Ehsan Hashemi; | arxiv-cs.RO | 2021-01-18 |
| 319 | HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network That Achieves Over 0.9 Mean Dice and 86 FPS IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new convolution neural network called HarDNet-MSEG for polyp segmentation. |
Chien-Hsiang Huang; Hung-Yu Wu; Youn-Long Lin; | arxiv-cs.CV | 2021-01-18 |
| 320 | Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to leverage multi-modality for domain adaptation, we propose cross-modal learning, where we enforce consistency between the predictions of two modalities via mutual mimicking. |
Maximilian Jaritz; Tuan-Hung Vu; Raoul de Charette; Émilie Wirbel; Patrick Pérez; | arxiv-cs.CV | 2021-01-18 |
| 321 | Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an active learning approach to maximize model performance given limited annotation budgets. |
XIAN SHI et. al. | arxiv-cs.CV | 2021-01-18 |
| 322 | SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular Images IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The state-of-the-art methods employ multi-task learning to simultaneously learn models for these two tasks at the pixel-wise level. |
Lei He; Jiwen Lu; Guanghui Wang; Shiyu Song; Jie Zhou; | arxiv-cs.CV | 2021-01-18 |
| 323 | Self-Supervised Representation Learning from Flow Equivariance IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this ability, we present a new self-supervised learning representation framework that can be directly deployed on a video stream of complex scenes with many moving objects. |
Yuwen Xiong; Mengye Ren; Wenyuan Zeng; Raquel Urtasun; | arxiv-cs.CV | 2021-01-16 |
| 324 | VideoClick: Video Object Segmentation with A Single Click IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Towards this goal, in this paper we propose a bottom up approach where given a single click for each object in a video, we obtain the segmentation masks of these objects in the full video. |
Namdar Homayounfar; Justin Liang; Wei-Chiu Ma; Raquel Urtasun; | arxiv-cs.CV | 2021-01-16 |
| 325 | Semi Supervised Deep Quick Instance Detection and Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a semi supervised deep quick learning framework for instance detection and pixel-wise semantic segmentation of images in a dense clutter of items. |
Ashish Kumar; L. Behera; | arxiv-cs.CV | 2021-01-16 |
| 326 | PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this article, we introduce a high-efficient development toolkit for image segmentation, named PaddleSeg. Furthermore, we provide comprehensive benchmarks and evaluations to show that these segmentation algorithms trained on our toolkit have more competitive accuracy. |
YI LIU et. al. | arxiv-cs.CV | 2021-01-15 |
| 327 | Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this problem, we propose novel deep dual-resolution networks (DDRNets) for real-time semantic segmentation of road scenes. |
YUANDUO HONG et. al. | arxiv-cs.CV | 2021-01-15 |
| 328 | U-Noise: Learnable Noise Masks for Interpretable Image Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new method for interpreting image segmentation models by learning regions of images in which noise can be applied without hindering downstream model performance. |
Teddy Koker; Fatemehsadat Mireshghallah; Tom Titcombe; Georgios Kaissis; | arxiv-cs.CV | 2021-01-14 |
| 329 | Road Surface Translation Under Snow-covered and Semantic Segmentation for Snow Hazard Index IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This study proposes a deep learning application with live image post-processing to automatically calculate a snow hazard ratio indicator. |
Takato Yasuno; Junichiro Fujii; Hiroaki Sugawara; Masazumi Amakata; | arxiv-cs.CV | 2021-01-14 |
| 330 | DuctTake: Spatiotemporal Video Compositing IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We describe in detail the required components, decisions, and new techniques that together make a usable, interactive tool for compositing HD video, paying special attention to running time and performance of each section. |
Jan Rueegg; Oliver Wang; Aljoscha Smolic; Markus Gross; | arxiv-cs.CV | 2021-01-12 |
| 331 | Rethinking Interactive Image Segmentation: Feature Space Annotation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We take a step back to propose interactive and simultaneous segment annotation from multiple images guided by feature space projection and optimized by metric learning as the labeling progresses. |
Jordão Bragantini; Alexandre Falcão; Laurent Najman; | arxiv-cs.CV | 2021-01-12 |
| 332 | Boundary-Aware Segmentation Network for Mobile and Web Applications IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a simple yet powerful Boundary-Aware Segmentation Network (BASNet), which comprises a predict-refine architecture and a hybrid loss, for highly accurate image segmentation. |
XUEBIN QIN et. al. | arxiv-cs.CV | 2021-01-12 |
| 333 | Spherical Transformer: Adapting Spherical Signal to CNNs IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present Spherical Transformer which can transform spherical signals into vectors that can be directly processed by standard CNNs such that many well-designed CNNs architectures can be reused across tasks and datasets by pretraining. |
Haikuan Du; Hui Cao; Shen Cai; Junchi Yan; Siyu Zhang; | arxiv-cs.CV | 2021-01-11 |
| 334 | The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The goal of this article is to illuminate the vulnerability aspects of CNNs used for semantic segmentation with respect to adversarial attacks, and share insights into some of the existing known adversarial defense strategies. |
ANDREAS BÄR et. al. | arxiv-cs.CV | 2021-01-11 |
| 335 | ORDNet: Capturing Omni-Range Dependencies for Scene Parsing IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Existing methods can effectively capture long-range dependencies with self-attention mechanism while short ones by local convolution. |
SHAOFEI HUANG et. al. | arxiv-cs.CV | 2021-01-11 |
| 336 | Semantic Segmentation of Remote Sensing Images with Sparse Annotations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate such a burden, we propose a framework for semantic segmentation of aerial images based on incomplete annotations, where annotators are asked to label a few pixels with easy-to-draw scribbles. |
Yuansheng Hua; Diego Marcos; Lichao Mou; Xiao Xiang Zhu; Devis Tuia; | arxiv-cs.CV | 2021-01-10 |
| 337 | HIVE-Net: Centerline-Aware HIerarchical View-Ensemble Convolutional Network for Mitochondria Segmentation in EM Images IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we introduce a centerline-aware multitask network by utilizing centerline as an intrinsic shape cue of mitochondria to regularize the segmentation. |
Zhimin Yuan; Xiaofen Ma; Jiajin Yi; Zhengrong Luo; Jialin Peng; | arxiv-cs.CV | 2021-01-08 |
| 338 | Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Built upon the boundary-aware GEM, we build our network and test it on benchmarks like ScanNet v2, S3DIS. |
JINGYU GONG et. al. | arxiv-cs.CV | 2021-01-07 |
| 339 | A Robust Illumination-Invariant Camera System for Agricultural Applications IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a high throughput robust active lighting-based camera system that generates consistent images in all lighting conditions. |
Abhisesh Silwal; Tanvir Parhar; Francisco Yandun; George Kantor; | arxiv-cs.CV | 2021-01-06 |
| 340 | Generating Masks from Boxes By Mining Spatio-Temporal Consistencies in Videos IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a method for generating segmentation masks from per-frame bounding box annotations in videos. |
Bin Zhao; Goutam Bhat; Martin Danelljan; Luc Van Gool; Radu Timofte; | arxiv-cs.CV | 2021-01-06 |
| 341 | RethNet: Object-by-Object Learning for Detecting Facial Skin Problems IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a concept of object-by-object learning technique to detect 11 types of facial skin lesions using semantic segmentation methods. |
Shohrukh Bekmirzaev; Seoyoung Oh; Sangwook Yoo; | arxiv-cs.CV | 2021-01-06 |
| 342 | Local Memory Attention for Fast Video Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel neural network module that transforms an existing single-frame semantic segmentation model into a video semantic segmentation pipeline. |
Matthieu Paul; Martin Danelljan; Luc Van Gool; Radu Timofte; | arxiv-cs.CV | 2021-01-05 |
| 343 | Deep Class-Specific Affinity-Guided Convolutional Network for Multimodal Unpaired Image Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an affinity-guided fully convolutional network for multimodal image segmentation. |
Jingkun Chen; Wenqi Li; Hongwei Li; Jianguo Zhang; | arxiv-cs.CV | 2021-01-05 |
| 344 | A Framework for Fast Scalable BNN Inference Using Googlenet and Transfer Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The work in this thesis aims to achieve high accuracy in object detection with good real-time performance. |
Karthik E; | arxiv-cs.CV | 2021-01-04 |
| 345 | Privacy Preserving Domain Adaptation For Semantic Segmentation Of Medical Images IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop an algorithm for UDA in a privacy-constrained setting, where the source domain data is inaccessible. |
Serban Stan; Mohammad Rostami; | arxiv-cs.CV | 2021-01-02 |
| 346 | Energy-constrained Self-training For Unsupervised Domain Adaptation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we resort to the energy-based model and constrain the training of the unlabeled target sample with the energy function minimization objective. |
XIAOFENG LIU et. al. | arxiv-cs.CV | 2021-01-01 |
| 347 | Language-Mediated, Object-Centric Representation Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Language-mediated, Object-centric Representation Learning (LORL), a paradigm for learning disentangled, object-centric scene representations from vision and language. |
Ruocheng Wang; Jiayuan Mao; Samuel J. Gershman; Jiajun Wu; | arxiv-cs.LG | 2020-12-31 |
| 348 | Rethinking Semantic Segmentation from A Sequence-to-Sequence Perspective with Transformers IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task. |
SIXIAO ZHENG et. al. | arxiv-cs.CV | 2020-12-31 |
| 349 | SALA: Soft Assignment Local Aggregation for Parameter Efficient 3D Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on designing a point local aggregation function that yields parameter efficient networks for 3D point cloud semantic segmentation. |
Hani Itani; Silvio Giancola; Ali Thabet; Bernard Ghanem; | arxiv-cs.CV | 2020-12-29 |
| 350 | Deep Visual Domain Adaptation IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The aim of this paper, therefore, is to give a comprehensive overview of deep domain adaptation methods for computer vision applications. |
Gabriela Csurka; | arxiv-cs.CV | 2020-12-28 |
| 351 | Compositional Prototype Network With Multi-view Comparision For Few-Shot Point Cloud Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present the Compositional Prototype Network that can undertake point cloud segmentation with only a few labeled training data. To evaluate the proposed method, we create a new segmentation benchmark dataset, ScanNet-$6^i$, which is built upon ScanNet dataset. |
Xiaoyu Chen; Chi Zhang; Guosheng Lin; Jing Han; | arxiv-cs.CV | 2020-12-28 |
| 352 | Spectral Analysis For Semantic Segmentation With Applications On Feature Truncation And Weak Annotation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we advance to have a deeper investigation on the sampling efficiency of the down-sampled grid. |
Li-Wei Chen; Wei-Chen Chiu; Chin-Tien Wu; | arxiv-cs.CV | 2020-12-28 |
| 353 | Semantic Segmentation On Swiss3DCities: A Benchmark Study On Aerial Photogrammetric 3D Pointcloud Dataset IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new outdoor urban 3D pointcloud dataset, covering a total area of 2.7 $km^2$, sampled from three Swiss cities with different characteristics. |
Gülcan Can; Dario Mantegazza; Gabriele Abbate; Sébastien Chappuis; Alessandro Giusti; | arxiv-cs.CV | 2020-12-23 |
| 354 | Unsupervised Domain Adaptation For Semantic Segmentation By Content Transfer IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we tackle the unsupervised domain adaptation (UDA) for semantic segmentation, which aims to segment the unlabeled real data using labeled synthetic data. |
Suhyeon Lee; Junhyuk Hyun; Hongje Seong; Euntai Kim; | arxiv-cs.CV | 2020-12-23 |
| 355 | ICMSC: Intra- And Cross-modality Semantic Consistency For Unsupervised Domain Adaptation On Hip Joint Bone Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose intra- and cross-modality semantic consistency (ICMSC) for UDA and our key insight is that the segmentation of synthesised images in different styles should be consistent. |
GUODONG ZENG et. al. | arxiv-cs.CV | 2020-12-23 |
| 356 | Warping Of Radar Data Into Camera Image For Cross-Modal Supervision In Automotive Applications IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel framework to project automotive radar range-Doppler (RD) spectrum into camera image. |
CHRISTOPHER GRIMM et. al. | arxiv-cs.CV | 2020-12-23 |
| 357 | Low-latency Perception In Off-Road Dynamical Low Visibility Environments IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this research, the authors have investigated the behavior of Deep Learning algorithms applied to semantic segmentation of off-road environments and unpaved roads under differents adverse conditions of visibility. |
NELSON ALVES et. al. | arxiv-cs.CV | 2020-12-23 |
| 358 | CholecSeg8k: A Semantic Segmentation Dataset For Laparoscopic Cholecystectomy Based On Cholec80 IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This article elaborates on the efforts of preparing the dataset for semantic segmentation, which is the foundation of many computer-assisted surgery mechanisms. |
W. -Y. HONG et. al. | arxiv-cs.CV | 2020-12-22 |
| 359 | Learning Dynamic Network Using A Reuse Gate Function in Semi-supervised Video Object Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we exploit this observation by using temporal information to quickly identify frames with minimal change and skip the heavyweight mask generation step. |
Hyojin Park; Jayeon Yoo; Seohyeong Jeong; Ganesh Venkatesh; Nojun Kwak; | arxiv-cs.CV | 2020-12-21 |
| 360 | Contraband Materials Detection Within Volumetric 3D Computed Tomography Baggage Security Screening Imagery IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast to the original dense representation form of volumetric 3D CT data, we propose to convert the CT volumes into sparse point clouds which allows the use of point cloud processing approaches such as PointNet++ towards more efficient processing. |
Qian Wang; Toby P. Breckon; | arxiv-cs.CV | 2020-12-21 |
| 361 | HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel, real-time, semantic segmentation network in which the encoder both encodes and generates the parameters (weights) of the decoder. |
Yuval Nirkin; Lior Wolf; Tal Hassner; | arxiv-cs.CV | 2020-12-21 |
| 362 | Leaf Segmentation And Counting With Deep Learning: On Model Certainty, Test-Time Augmentation, Trade-Offs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Despite good efforts from research groups, one of the main challenges for proposing better methods is still the limitation of labelled data availability. |
Douglas Pinto Sampaio Gomes; Lihong Zheng; | arxiv-cs.CV | 2020-12-21 |
| 363 | Anchor-Based Spatial-Temporal Attention Convolutional Networks For Dynamic 3D Point Cloud Sequences Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: An Anchor-based Spatial-Temporal Attention Convolution operation (ASTAConv) is proposed in this paper to process dynamic 3D point cloud sequences. |
GUANGMING WANG et. al. | arxiv-cs.CV | 2020-12-20 |
| 364 | Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we present a framework for semi-supervised semantic segmentation, which is enhanced by self-supervised monocular depth estimation from unlabeled image sequences. |
LUKAS HOYER et. al. | arxiv-cs.CV | 2020-12-19 |
| 365 | A Light Field Front-end For Robust SLAM In Dynamic Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a Light Field SLAM front-end which is robust to dynamic environments. |
Pushyami Kaveti; Hanumant Singh; | arxiv-cs.RO | 2020-12-19 |
| 366 | SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we discover that the locations of instances matter for 3D scene segmentation. |
An Tao; Yueqi Duan; Yi Wei; Jiwen Lu; Jie Zhou; | arxiv-cs.CV | 2020-12-18 |
| 367 | A Holistically-Guided Decoder For Deep Representation Learning With Applications To Semantic Segmentation And Object Detection IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose one novel holistically-guided decoder which is introduced to obtain the high-resolution semantic-rich feature maps via the multi-scale features from the encoder. |
Jianbo Liu; Sijie Ren; Yuanjie Zheng; Xiaogang Wang; Hongsheng Li; | arxiv-cs.CV | 2020-12-18 |
| 368 | Hyperspectral Image Semantic Segmentation In Cityscapes IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on a novel topic, semi-supervised semantic segmentation in cityscapes using HSIs.It is based on the idea that high-resolution HSIs in city scenes contain rich spectral information, which can be easily associated to semantics without manual labeling. |
YUXING HUANG et. al. | arxiv-cs.CV | 2020-12-18 |
| 369 | LGENet: Local And Global Encoder Network For Semantic Segmentation Of Airborne Laser Scanning Point Clouds IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a local and global encoder network (LGENet) for semantic segmentation of ALS point clouds. |
Yaping Lin; George Vosselman; Yanpeng Cao; Michael Ying Yang; | arxiv-cs.CV | 2020-12-18 |
| 370 | Quantifying The Unknown: Impact of Segmentation Uncertainty on Image-Based Simulations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Through the creation and sampling of segmentation uncertainty probability maps, we systematically and objectively create uncertainty distributions of the physics quantities. |
MICHAEL C. KRYGIER et. al. | arxiv-cs.CE | 2020-12-17 |
| 371 | Self-supervised Learning With Fully Convolutional Networks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on the problem of learning representation from unlabeled data for semantic segmentation. |
Zhengeng Yang; Hongshan Yu; Yong He; Zhi-Hong Mao; Ajmal Mian; | arxiv-cs.CV | 2020-12-17 |
| 372 | Firearm Detection Via Convolutional Neural Networks: Comparing A Semantic Segmentation Model Against End-to-End Solutions IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we conduct a comparison between a traditional monolithic end-to-end deep learning model and a previously proposed model based on an ensemble of simpler neural networks detecting fire-weapons via semantic segmentation. |
Alexander Egiazarov; Fabio Massimo Zennaro; Vasileios Mavroeidis; | arxiv-cs.CV | 2020-12-17 |
| 373 | Embodied Visual Active Learning For Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We extensively evaluate the proposed models using the photorealistic Matterport3D simulator and show that a fully learnt method outperforms comparable pre-specified counterparts, even when requesting fewer annotations. |
David Nilsson; Aleksis Pirinen; Erik Gärtner; Cristian Sminchisescu; | arxiv-cs.CV | 2020-12-17 |
| 374 | Unsupervised Image Segmentation Using Mutual Mean-Teaching IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose an unsupervised image segmentation model based on the Mutual Mean-Teaching (MMT) framework to produce more stable results. |
Zhichao Wu; Lei Guo; Hao Zhang; Dan Xu; | arxiv-cs.CV | 2020-12-16 |
| 375 | Unlabeled Data Guided Semi-supervised Histopathology Image Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new data guided generative method for histopathology image segmentation by leveraging the unlabeled data distributions. |
HONGXIAO WANG et. al. | arxiv-cs.CV | 2020-12-16 |
| 376 | Semi-Global Shape-aware Network IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Semi-Global Shape-aware Network (SGSNet) considering both feature similarity and proximity for preserving object shapes when modeling long-range dependencies. |
Pengju Zhang; Yihong Wu; Jiagang Zhu; | arxiv-cs.CV | 2020-12-16 |
| 377 | S3CNet: A Sparse Semantic Scene Completion Network For LiDAR Point Clouds IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we formulate a method that subsumes the sparsity of large-scale environments and present S3CNet, a sparse convolution based neural network that predicts the semantically completed scene from a single, unified LiDAR point cloud. |
Ran Cheng; Christopher Agia; Yuan Ren; Xinhai Li; Liu Bingbing; | arxiv-cs.CV | 2020-12-16 |
| 378 | Point Transformer IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by this success, we investigate the application of self-attention networks to 3D point cloud processing. |
Hengshuang Zhao; Li Jiang; Jiaya Jia; Philip Torr; Vladlen Koltun; | arxiv-cs.CV | 2020-12-16 |
| 379 | Exploring Data-Efficient 3D Scene Understanding With Contrastive Scene Contexts IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore data-efficient learning for 3D point cloud. |
Ji Hou; Benjamin Graham; Matthias Nießner; Saining Xie; | arxiv-cs.CV | 2020-12-16 |
| 380 | Cluster, Split, Fuse, And Update: Meta-Learning For Open Compound Domain Adaptive Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a principled meta-learning based approach to OCDA for semantic segmentation, MOCDA, by modeling the unlabeled target domain continuously. |
RUI GONG et. al. | arxiv-cs.CV | 2020-12-15 |
| 381 | MDALU: Multi-Source Domain Adaptation And Label Unification With Partial Datasets IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper treats this task as a multi-source domain adaptation and label unification (mDALU) problem and proposes a novel method for it. |
Rui Gong; Dengxin Dai; Yuhua Chen; Wen Li; Luc Van Gool; | arxiv-cs.CV | 2020-12-15 |
| 382 | Cross-Domain Grouping And Alignment For Domain Adaptive Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this limitation, we introduce a learnable clustering module, and a novel domain adaptation framework called cross-domain grouping and alignment. |
MINSU KIM et. al. | arxiv-cs.CV | 2020-12-15 |
| 383 | CosSGD: Nonlinear Quantization For Communication-efficient Federated Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a nonlinear quantization for compressed stochastic gradient descent, which can be easily utilized in federated learning. |
Yang He; Maximilian Zenk; Mario Fritz; | arxiv-cs.LG | 2020-12-15 |
| 384 | Pyramid-Focus-Augmentation: Medical Image Segmentation With Step-Wise Focus IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present our solution for the Medico 2020 task, which focused on the problem of colon polyp segmentation. |
Vajira Thambawita; Steven Hicks; Pål Halvorsen; Michael A. Riegler; | arxiv-cs.CV | 2020-12-14 |
| 385 | Semantic-Guided Representation Enhancement For Self-supervised Monocular Trained Depth Estimation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address this problem by proposing a semantic-guided depth representation enhancement method, which promotes both local and global depth feature representations by leveraging rich contextual information. |
RUI LI et. al. | arxiv-cs.CV | 2020-12-14 |
| 386 | Image Inpainting Guided By Coherence Priors Of Semantics And Textures IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce coherence priors between the semantics and textures which make it possible to concentrate on completing separate textures in a semantic-wise manner. |
Liang Liao; Jing Xiao; Zheng Wang; Chia-Wen Lin; Shin’ichi Satoh; | arxiv-cs.CV | 2020-12-14 |
| 387 | Information-Theoretic Segmentation By Inpainting Error Maximization IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study image segmentation from an information-theoretic perspective, proposing a novel adversarial method that performs unsupervised segmentation by partitioning images into maximally independent sets. |
Pedro Savarese; Sunnie S. Y. Kim; Michael Maire; Greg Shakhnarovich; David McAllester; | arxiv-cs.CV | 2020-12-14 |
| 388 | Scaling Semantic Segmentation Beyond 1K Classes on A Single GPU IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel training methodology to train and scale the existing semantic segmentation models for a large number of semantic classes without increasing the memory overhead. |
Shipra Jain; Danda Paudel Pani; Martin Danelljan; Luc Van Gool; | arxiv-cs.CV | 2020-12-14 |
| 389 | Contrastive Learning for Label-Efficient Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a simple and effective contrastive learning-based training strategy in which we first pretrain the network using a pixel-wise, label-based contrastive loss, and then fine-tune it using the cross-entropy loss. |
XIANGYUN ZHAO et. al. | arxiv-cs.CV | 2020-12-13 |
| 390 | Iterative Knowledge Exchange Between Deep Learning And Space-Time Spectral Clustering For Unsupervised Segmentation In Videos IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a dual system for unsupervised object segmentation in video, which brings together two modules with complementary properties: a space-time graph that discovers objects in videos and a deep network that learns powerful object features. |
Emanuela Haller; Adina Magda Florea; Marius Leordeanu; | arxiv-cs.CV | 2020-12-13 |
| 391 | Vision Based Adaptation To Kernelized Synergies For Human Inspired Robotic Manipulation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address such limitations, this research proposes to augment the previously developed kernelized synergies framework with visual perception to automatically adapt to the unknown objects. |
Sunny Katyara; Fanny Ficuciello; Fei Chen; Bruno Siciliano; Darwin G. Caldwell; | arxiv-cs.RO | 2020-12-13 |
| 392 | Meticulous Object Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose and study a task named Meticulous Object Segmentation (MOS), which is focused on segmenting well-defined foreground objects with elaborate shapes in high resolution images (e.g. 2k – 4k). In addition, we collect a MOS benchmark dataset including 600 high quality images with complex objects. |
CHENGLIN YANG et. al. | arxiv-cs.CV | 2020-12-13 |
| 393 | Classifying Breast Histopathology Images With A Ductal Instance-Oriented Pipeline IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose the Ductal Instance-Oriented Pipeline (DIOP) that contains a duct-level instance segmentation model, a tissue-level semantic segmentation model, and three-levels of features for diagnostic classification. |
BEIBIN LI et. al. | arxiv-cs.CV | 2020-12-11 |
| 394 | Confidence Estimation Via Auxiliary Models IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a novel target criterion for model confidence, namely the true class probability (TCP). |
CHARLES CORBIÈRE et. al. | arxiv-cs.CV | 2020-12-11 |
| 395 | Spatiotemporal Graph Neural Network Based Mask Reconstruction For Video Object Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel spatiotemporal graph neural network (STG-Net) to reconstruct more accurate masks for video object segmentation, which captures the local contexts by utilizing all proposals. |
DAIZONG LIU et. al. | arxiv-cs.CV | 2020-12-10 |
| 396 | Full-Glow: Fully Conditional Glow For More Realistic Image Generation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose Full-Glow, a fully conditional Glow-based architecture for generating plausible and realistic images of novel street scenes given a semantic segmentation map indicating the scene layout. |
Moein Sorkhei; Gustav Eje Henter; Hedvig Kjellström; | arxiv-cs.CV | 2020-12-10 |
| 397 | Self-Supervised Learning Of Lidar Segmentation For Autonomous Indoor Navigation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a self-supervised learning approach for the semantic segmentation of lidar frames. |
Hugues Thomas; Ben Agro; Mona Gridseth; Jian Zhang; Timothy D. Barfoot; | arxiv-cs.RO | 2020-12-10 |
| 398 | Exploiting Diverse Characteristics and Adversarial Ambivalence for Domain Adaptive Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a condition-guided adaptation framework that is empowered by a special attentive progressive adversarial training (APAT) mechanism and a novel self-training policy. |
BOWEN CAI et. al. | arxiv-cs.CV | 2020-12-10 |
| 399 | Few-shot Medical Image Segmentation Using A Global Correlation Network With Discriminative Embedding IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we proposed a novel method for few-shot medical image segmentation, which enables a segmentation model to fast generalize to an unseen class with few training images. |
LIYAN SUN et. al. | arxiv-cs.CV | 2020-12-09 |
| 400 | Competitive Simplicity For Multi-Task Learning For Real-Time Foggy Scene Understanding Via Domain Adaptation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a complex but competitive multi-task learning approach capable of performing in real-time semantic scene understanding and monocular depth estimation under foggy weather conditions by leveraging both recent advances in adversarial training and domain adaptation. |
Naif Alshammari; Samet Akcay; Toby P. Breckon; | arxiv-cs.CV | 2020-12-09 |
| 401 | Multi-Model Learning For Real-Time Automotive Semantic Foggy Scene Understanding Via Domain Adaptation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an efficient end-to-end automotive semantic scene understanding approach that is robust to foggy weather conditions. |
Naif Alshammari; Samet Akcay; Toby P. Breckon; | arxiv-cs.CV | 2020-12-09 |
| 402 | Group-Wise Semantic Mining For Weakly Supervised Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Acquiring sufficient ground-truth supervision to train deep visual models has been a bottleneck over the years due to the data-hungry nature of deep learning. |
Xueyi Li; Tianfei Zhou; Jianwu Li; Yi Zhou; Zhaoxiang Zhang; | arxiv-cs.CV | 2020-12-09 |
| 403 | AMVNet: Assertion-based Multi-View Fusion Network For LiDAR Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an Assertion-based Multi-View Fusion network (AMVNet) for LiDAR semantic segmentation which aggregates the semantic features of individual projection-based networks using late fusion. |
Venice Erin Liong; Thi Ngoc Tho Nguyen; Sergi Widjaja; Dhananjai Sharma; Zhuang Jie Chong; | arxiv-cs.CV | 2020-12-09 |
| 404 | Scale Aware Adaptation For Land-Cover Classification In Remote Sensing Imagery IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We therefore propose a scale aware adversarial learning framework to perform joint cross-location and cross-scale land-cover classification. |
Xueqing Deng; Yi Zhu; Yuxin Tian; Shawn Newsam; | arxiv-cs.CV | 2020-12-08 |
| 405 | Towards Uncovering The Intrinsic Data Structures for Unsupervised Domain Adaptation Using Structurally Regularized Deep Clustering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Technically, we propose a hybrid model of Structurally Regularized Deep Clustering, which integrates the regularized discriminative clustering of target data with a generative one, and we thus term our method as H-SRDC. |
Hui Tang; Xiatian Zhu; Ke Chen; Kui Jia; C. L. Philip Chen; | arxiv-cs.CV | 2020-12-08 |
| 406 | You Only Need Adversarial Supervision for Semantic Image Synthesis IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel, simplified GAN model, which needs only adversarial supervision to achieve high quality results. |
VADIM SUSHKO et. al. | arxiv-cs.CV | 2020-12-08 |
| 407 | Sparse Single Sweep LiDAR Point Cloud Segmentation Via Learning Contextual Shape Priors From Scene Completion IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel sparse LiDAR point cloud semantic segmentation framework assisted by learned contextual shape priors. |
XU YAN et. al. | arxiv-cs.CV | 2020-12-07 |
| 408 | Rethinking Learnable Tree Filter For Generic Feature Transform IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation. |
LIN SONG et. al. | arxiv-cs.CV | 2020-12-07 |
| 409 | Rotation-Invariant Point Convolution With Multiple Equivariant Alignments IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we study the relation between equivariance and invariance in 3D point convolutions. |
Hugues Thomas; | arxiv-cs.CV | 2020-12-07 |
| 410 | Ada-Segment: Automated Multi-loss Adaptation For Panoptic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The extensive ablation studies reveal the ever-changing dynamics throughout the training process, necessitating the incorporation of an automated and adaptive learning strategy as presented in this paper. |
GENGWEI ZHANG et. al. | arxiv-cs.CV | 2020-12-07 |
| 411 | TediGAN: Text-Guided Diverse Face Image Generation and Manipulation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose TediGAN, a novel framework for multi-modal image generation and manipulation with textual descriptions. |
Weihao Xia; Yujiu Yang; Jing-Hao Xue; Baoyuan Wu; | arxiv-cs.CV | 2020-12-06 |
| 412 | Self-Training for Class-Incremental Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose to apply a self-training approach that leverages unlabeled data, which is used for rehearsal of previous knowledge. |
Lu Yu; Xialei Liu; Joost van de Weijer; | arxiv-cs.CV | 2020-12-06 |
| 413 | FloodNet: A High Resolution Aerial Imagery Dataset For Post Flood Scene Understanding IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we compare and contrast the performances of baseline methods for image classification, semantic segmentation, and visual question answering on our dataset. |
MARYAM RAHNEMOONFAR et. al. | arxiv-cs.CV | 2020-12-05 |
| 414 | Semantic Segmentation Of Medium-Resolution Satellite Imagery Using Conditional Generative Adversarial Networks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by Conditional Generative Adversarial Networks (CGAN) based approach of image-to-image translation for high-resolution satellite imagery, we propose a CGAN framework for land cover classification using medium-resolution Sentinel-2 imagery. |
Aditya Kulkarni; Tharun Mohandoss; Daniel Northrup; Ernest Mwebaze; Hamed Alemohammad; | arxiv-cs.CV | 2020-12-05 |
| 415 | F2Net: Learning To Focus On The Foreground For Unsupervised Video Object Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate these issues, we propose a novel Focus on Foreground Network (F2Net), which delves into the intra-inter frame details for the foreground objects and thus effectively improve the segmentation performance. |
Daizong Liu; Dongdong Yu; Changhu Wang; Pan Zhou; | arxiv-cs.CV | 2020-12-04 |
| 416 | Encoding The Latent Posterior of Bayesian Neural Networks for Uncertainty Quantification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we aim for efficient deep BNNs amenable to complex computer vision architectures, e.g. ResNet50 DeepLabV3+, and tasks, e.g. semantic segmentation, with fewer assumptions on the parameters. |
Gianni Franchi; Andrei Bursuc; Emanuel Aldea; Severine Dubuisson; Isabelle Bloch; | arxiv-cs.CV | 2020-12-04 |
| 417 | On The Surprising Efficiency of Committee-based Models IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To fill this gap, we conduct a comprehensive analysis of the efficiency of committee-based models and find that committee-based models provide a complementary paradigm to achieve superior efficiency without tuning the architecture: a simple ensemble or cascade of existing networks can be considerably more efficient than state-of-the-art single models, even outperforming sophisticated neural architecture search methods. |
XIAOFANG WANG et. al. | arxiv-cs.CV | 2020-12-03 |
| 418 | Make One-Shot Video Object Segmentation Efficient Again IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate the inefficiencies of previous fine-tuning approaches, we present efficient One-Shot Video Object Segmentation (e-OSVOS). |
Tim Meinhardt; Laura Leal-Taixe; | arxiv-cs.CV | 2020-12-03 |
| 419 | Domain Adaptation On Semantic Segmentation For Aerial Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel unsupervised domain adaptation framework to address domain shift in the context of aerial semantic image segmentation. |
Ying Chen; Xu Ouyang; Kaiyue Zhu; Gady Agam; | arxiv-cs.CV | 2020-12-03 |
| 420 | Single-shot Path Integrated Panoptic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to resolve panoptic segmentation in single-shot by integrating the execution flows. |
Sukjun Hwang; Seoung Wug Oh; Seon Joo Kim; | arxiv-cs.CV | 2020-12-02 |
| 421 | Chair Segments: A Compact Benchmark For The Study Of Object Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce ChairSegments, a novel and compact semi-synthetic dataset for object segmentation. |
Leticia Pinto-Alva; Ian K. Torres; Rosangel Garcia; Ziyan Yang; Vicente Ordonez; | arxiv-cs.CV | 2020-12-02 |
| 422 | From A Fourier-Domain Perspective on Adversarial Examples to A Wiener Filter Defense for Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study the adversarial problem from a frequency domain perspective. |
NIKHIL KAPOOR et. al. | arxiv-cs.CV | 2020-12-02 |
| 423 | A Three-Stage Self-Training Framework For Semi-Supervised Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we address this problem by proposing a holistic solution framed as a three-stage self-training framework for semi-supervised semantic segmentation. |
Rihuan Ke; Angelica Aviles-Rivero; Saurabh Pandey; Saikumar Reddy; Carola-Bibiane Schönlieb; | arxiv-cs.CV | 2020-12-01 |
| 424 | 3D Guided Weakly Supervised Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a weakly supervised 2D semantic segmentation model by incorporating sparse bounding box labels with available 3D information, which is much easier to obtain with advanced sensors. |
Weixuan Sun; Jing Zhang; Nick Barnes; | arxiv-cs.CV | 2020-11-30 |
| 425 | Exploring Deep 3D Spatial Encodings For Large-Scale 3D Scene Understanding IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this letter, we have proposed an alternative approach to overcome the limitations of CNN based approaches by encoding the spatial features of raw 3D point clouds into undirected symmetrical graph models. |
Saqib Ali Khan; Yilei Shi; Muhammad Shahzad; Xiao Xiang Zhu; | arxiv-cs.CV | 2020-11-29 |
| 426 | UVid-Net: Enhanced Semantic Segmentation Of UAV Aerial Videos By Embedding Temporal Information IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, an enhanced encoder-decoder based CNN architecture (UVid-Net) is proposed for UAV video semantic segmentation. |
Girisha S; Ujjwal Verma; Manohara Pai M M; Radhika Pai; | arxiv-cs.CV | 2020-11-29 |
| 427 | Multi-stage Attention ResU-Net For Semantic Segmentation Of Fine-Resolution Remote Sensing Images IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this Letter, we propose a Linear Attention Mechanism (LAM) to address this issue, which is approximately equivalent to dot-product attention with computational efficiency. |
Rui Li; Shunyi Zheng; Chenxi Duan; Jianlin Su; Ce Zhang; | arxiv-cs.CV | 2020-11-29 |
| 428 | Training And Inference For Integer-Based Semantic Segmentation Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new quantization framework for training and inference of segmentation networks, where parameters and operations are constrained to 8-bit integer-based values for the first time. |
Jiayi Yang; Lei Deng; Yukuan Yang; Yuan Xie; Guoqi Li; | arxiv-cs.CV | 2020-11-29 |
| 429 | Multi-task GANs For Semantic Segmentation And Depth Completion With Cycle Consistency IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Semantic segmentation and depth completion are two challenging tasks in scene understanding, and they are widely used in robotics and autonomous driving. Although several works … |
CHONGZHEN ZHANG et. al. | arxiv-cs.CV | 2020-11-28 |
| 430 | Towards Robust Medical Image Segmentation On Small-Scale Data With Incomplete Labels IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To bridge the methodological gaps in label-efficient deep learning with partial supervision, we propose RAMP, a simple yet efficient data augmentation framework for partially supervised medical image segmentation by exploiting the assumption that patients share anatomical similarities. |
NANQING DONG et. al. | arxiv-cs.CV | 2020-11-28 |
| 431 | Spherical Interpolated Convolutional Network With Distance-Feature Density For 3D Semantic Segmentation Of Point Clouds IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a spherical interpolated convolution operator is proposed to replace the traditional grid-shaped 3D convolution operator. |
Guangming Wang; Yehui Yang; Huixin Zhang; Zhe Liu; Hesheng Wang; | arxiv-cs.CV | 2020-11-27 |
| 432 | Road Scene Graph: A Semantic Graph-Based Scene Representation Dataset For Intelligent Vehicles IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose road scene graph,a special scene-graph for intelligent vehicles. |
Yafu Tian; Alexander Carballo; Ruifeng Li; Kazuya Takeda; | arxiv-cs.CV | 2020-11-27 |
| 433 | Channel-wise Distillation for Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Observing that in semantic segmentation, some layers’ feature activations of each channel tend to encode saliency of scene categories (analogue to class activation mapping), we propose to align features channel-wise between the student and teacher networks. |
Changyong Shu; Yifan Liu; Jianfei Gao; Lin Xu; Chunhua Shen; | arxiv-cs.CV | 2020-11-26 |
| 434 | Polarization-driven Semantic Segmentation Via Efficient Attention-bridged Fusion IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thereby, in this work, we present EAFNet, an Efficient Attention-bridged Fusion Network to exploit complementary information coming from different optical sensors. By using a single-shot polarization sensor, we build the first RGB-P dataset which consists of 394 annotated pixel-aligned RGB-Polarization images. |
Kaite Xiang; Kailun Yang; Kaiwei Wang; | arxiv-cs.CV | 2020-11-26 |
| 435 | PGL: Prior-Guided Local Self-supervised Learning For 3D Medical Image Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a PriorGuided Local (PGL) self-supervised model that learns the region-wise local consistency in the latent feature space. |
Yutong Xie; Jianpeng Zhang; Zehui Liao; Yong Xia; Chunhua Shen; | arxiv-cs.CV | 2020-11-25 |
| 436 | Unsupervised Domain Adaptation In Semantic Segmentation Via Orthogonal And Clustered Embeddings IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose an effective Unsupervised Domain Adaptation (UDA) strategy, based on a feature clustering method that captures the different semantic modes of the feature distribution and groups features of the same class into tight and well-separated clusters. |
Marco Toldo; Umberto Michieli; Pietro Zanuttigh; | arxiv-cs.CV | 2020-11-25 |
| 437 | Fast Object Segmentation Learning with Kernel-based Methods for Robotics IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel architecture for object segmentation, that overcomes this problem and provides comparable performance in a fraction of the time required by the state-of-the-art methods. |
Federico Ceola; Elisa Maiettini; Giulia Pasquale; Lorenzo Rosasco; Lorenzo Natale; | arxiv-cs.CV | 2020-11-25 |
| 438 | AccSS3D: Accelerator For Spatially Sparse 3D DNNs IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present ACCELERATOR FOR SPATIALLY SPARSE 3D DNNs (AccSS3D), the first end-to-end solution for accelerating 3D scene understanding by exploiting the ample spatial sparsity. |
OM JI OMER et. al. | arxiv-cs.AR | 2020-11-25 |
| 439 | SegBlocks: Block-Based Dynamic Resolution Networks For Real-Time Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For instance, our method reduces the number of floating-point operations of SwiftNet-RN18 by 60% and increases the inference speed by 50%, with only 0.3% decrease in mIoU accuracy on Cityscapes. |
Thomas Verelst; Tinne Tuytelaars; | arxiv-cs.CV | 2020-11-24 |
| 440 | Multi-feature Driven Active Contour Segmentation Model For Infrared Image With Intensity Inhomogeneity IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a multi-feature driven active contour segmentation model to handle IR images with intensity inhomogeneity. |
QINYAN HUANG et. al. | arxiv-cs.CV | 2020-11-24 |
| 441 | Betrayed By Motion: Camouflaged Object Discovery Via Motion Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The objective of this paper is to design a computational architecture that discovers camouflaged objects in videos, specifically by exploiting motion information to perform object segmentation. (ii) We collect the first large-scale Moving Camouflaged Animals (MoCA) video dataset, which consists of over 140 clips across a diverse range of animals (67 categories). |
Hala Lamdouar; Charig Yang; Weidi Xie; Andrew Zisserman; | arxiv-cs.CV | 2020-11-23 |
| 442 | Scaling Wide Residual Networks for Panoptic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we revisit its architecture design for the recent challenging panoptic segmentation task, which aims to unify semantic segmentation and instance segmentation. |
Liang-Chieh Chen; Huiyu Wang; Siyuan Qiao; | arxiv-cs.CV | 2020-11-23 |
| 443 | PLOP: Learning Without Forgetting for Continual Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Local POD, a multi-scale pooling distillation scheme that preserves long- and short-range spatial relationships at feature level. |
Arthur Douillard; Yifu Chen; Arnaud Dapogny; Matthieu Cord; | arxiv-cs.CV | 2020-11-23 |
| 444 | Efficient Embedding Network For 3D Brain Tumor Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate a way to transfer the performance of a two-dimensional classiffication network for the purpose of three-dimensional semantic segmentation of brain tumors. |
HICHAM MESSAOUDI et. al. | arxiv-cs.CV | 2020-11-22 |
| 445 | Dense Open-set Recognition With Synthetic Outliers Generated By Real NVP IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present image classification experiments on CIFAR-10, as well as semantic segmentation experiments on three existing datasets (StreetHazards, WD-Pascal, Fishyscapes Lost & Found), and one contributed dataset. |
Matej Grcić; Petra Bevandić; Siniša Šegvić; | arxiv-cs.CV | 2020-11-22 |
| 446 | Segmentation Overlapping Wear Particles With Few Labelled Data And Imbalance Sample IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: An overlapping wear particle segmentation network (OWPSNet) is proposed in this study to segment the overlapped debris chains. |
Peng Peng; Jiugen Wang; | arxiv-cs.CV | 2020-11-20 |
| 447 | Bridging Scene Understanding And Task Execution With Flexible Simulation Environments IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To that end, we present TESSE (Task Execution with Semantic Segmentation Environments), an open source simulator for developing scene understanding and task execution algorithms. |
Zachary Ravichandran; J. Daniel Griffith; Benjamin Smith; Costas Frost; | arxiv-cs.RO | 2020-11-20 |
| 448 | DoDNet: Learning To Segment Multi-organ And Tumors From Multiple Partially Labeled Datasets IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we propose a dynamic on-demand network (DoDNet) that learns to segment multiple organs and tumors on partially labeled datasets. We have created a large-scale partially labeled dataset, termed MOTS, and demonstrated the superior performance of our DoDNet over other competitors on seven organ and tumor segmentation tasks. |
Jianpeng Zhang; Yutong Xie; Yong Xia; Chunhua Shen; | arxiv-cs.CV | 2020-11-19 |
| 449 | Unifying Instance And Panoptic Segmentation With Dynamic Rank-1 Convolutions IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we demonstrate that adding a single classification layer for semantic segmentation, fully-convolutional instance segmentation networks can achieve state-of-the-art panoptic segmentation quality. |
Hao Chen; Chunhua Shen; Zhi Tian; | arxiv-cs.CV | 2020-11-19 |
| 450 | Foreground-Aware Relation Network For Geospatial Object Segmentation In High Spatial Resolution Remote Sensing Imagery IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that the problems lie on the lack of foreground modeling and propose a foreground-aware relation network (FarSeg) from the perspectives of relation-based and optimization-based foreground modeling, to alleviate the above two problems. |
Zhuo Zheng; Yanfei Zhong; Junjue Wang; Ailong Ma; | arxiv-cs.CV | 2020-11-19 |
| 451 | Attention-Based Transformers For Instance Segmentation Of Cells In Microstructures IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel attention-based cell detection transformer (Cell-DETR) for direct end-to-end instance segmentation. |
Tim Prangemeier; Christoph Reich; Heinz Koeppl; | arxiv-cs.CV | 2020-11-19 |
| 452 | Geography-Aware Self-Supervised Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore their application to remote sensing, where unlabeled data is often abundant but labeled data is scarce. |
KUMAR AYUSH et. al. | arxiv-cs.CV | 2020-11-19 |
| 453 | Bidirectional RNN-based Few Shot Learning For 3D Medical Image Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a 3D few shot segmentation framework for accurate organ segmentation using limited training samples of the target organ annotation. |
Soopil Kim; Sion An; Philip Chikontwe; Sang Hyun Park; | arxiv-cs.CV | 2020-11-18 |
| 454 | Semantic Scene Completion Using Local Deep Implicit Functions on LiDAR Data IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a scene segmentation network based on local Deep Implicit Functions as a novel learning-based method for scene completion. |
Christoph B. Rist; David Emmerichs; Markus Enzweiler; Dariu M. Gavrila; | arxiv-cs.CV | 2020-11-18 |
| 455 | Dense Contrastive Learning for Self-Supervised Visual Pre-Training IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To fill this gap, we aim to design an effective, dense self-supervised learning method that directly works at the level of pixels (or local features) by taking into account the correspondence between local features. |
Xinlong Wang; Rufeng Zhang; Chunhua Shen; Tao Kong; Lei Li; | arxiv-cs.CV | 2020-11-18 |
| 456 | Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations And Dataset Biases IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Somewhat mysteriously the recent gains in performance come from training instance classification models, treating each image and it’s augmented versions as samples of a single class. In this work, we first present quantitative experiments to demystify these gains. |
Senthil Purushwalkam Shiva Prakash; Abhinav Gupta; | nips | 2020-11-17 |
| 457 | Uncertainty-Aware Learning For Zero-Shot Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we identify this challenge and address it with a novel framework that learns to discriminate noisy samples based on Bayesian uncertainty estimation. |
Ping Hu; Stan Sclaroff; Kate Saenko; | nips | 2020-11-17 |
| 458 | Causal Intervention For Weakly-Supervised Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). |
Dong Zhang; Hanwang Zhang; Jinhui Tang; Xian-Sheng Hua; Qianru Sun; | nips | 2020-11-17 |
| 459 | Make One-Shot Video Object Segmentation Efficient Again IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate the inefficiencies of previous fine-tuning approaches, we present efficient One-Shot Video Object Segmentation (e-OSVOS). |
Tim Meinhardt; Laura Leal-Taix�; | nips | 2020-11-17 |
| 460 | Delving Into The Cyclic Mechanism In Semi-supervised Video Object Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we take attempt to incorporate the cyclic mechanism with the vision task of semi-supervised video object segmentation. |
Yuxi Li; Ning Xu; Jinlong Peng; John See; Weiyao Lin; | nips | 2020-11-17 |
| 461 | Unsupervised BatchNorm Adaptation (UBNA): A Domain Adaptation Method For Semantic Segmentation Without Using Source Domain Representations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present a solution to the task of unsupervised domain adaptation (UDA) of a pre-trained semantic segmentation model without relying on any source domain representations. |
Marvin Klingner; Jan-Aike Termöhlen; Jacob Ritterbach; Tim Fingscheidt; | arxiv-cs.CV | 2020-11-17 |
| 462 | Auto-Panoptic: Cooperative Multi-Component Architecture Search For Panoptic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an efficient, cooperative and highly automated framework to simultaneously search for all main components including backbone, segmentation branches, and feature fusion module in a unified panoptic segmentation pipeline based on the prevailing one-shot Network Architecture Search (NAS) paradigm. |
Yangxin Wu; Gengwei Zhang; Hang Xu; Xiaodan Liang; Liang Lin; | nips | 2020-11-17 |
| 463 | Multi Receptive Field Network For Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the first issue, we propose a new Multi-Receptive Field Module (MRFM), explicitly taking multi-scale features into account. |
Yuan Jianlong; Zelu Deng; Wang Shu; Luo Zhenbo; | arxiv-cs.CV | 2020-11-17 |
| 464 | Pixel-Level Cycle Association: A New Perspective For Domain Adaptive Semantic Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to build the pixel-level cycle association between source and target pixel pairs and contrastively strengthen their connections to diminish the domain gap and make the features more discriminative. |
Guoliang Kang; Yunchao Wei; Yi Yang; Yueting Zhuang; Alexander Hauptmann; | nips | 2020-11-17 |
| 465 | Video Object Segmentation With Adaptive Feature Bank And Uncertain-Region Refinement IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a new matching-based framework for semi-supervised video object segmentation (VOS). |
Yongqing Liang; Xin Li; Navid Jafari; Jim Chen; | nips | 2020-11-17 |
| 466 | Learning Physical Graph Representations From Visual Scenes IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these limitations, we introduce the idea of “Physical Scene Graphs” (PSGs), which represent scenes as hierarchical graphs, with nodes in the hierarchy corresponding intuitively to object parts at different scales, and edges to physical connections between parts. |
DANIEL BEAR et. al. | nips | 2020-11-17 |
| 467 | Contrastive Learning Of Global And Local Features For Medical Image Segmentation With Limited Annotations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose strategies for extending the contrastive learning framework for segmentation of volumetric medical images in the semi-supervised setting with limited annotations, by leveraging domain-specific and problem-specific cues. |
Krishna Chaitanya; Ertunc Erdil; Neerav Karani; Ender Konukoglu; | nips | 2020-11-17 |
| 468 | RELLIS-3D Dataset: Data, Benchmarks and Analysis IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This novel dataset provides the resources needed by researchers to continue to develop more advanced algorithms and investigate new research directions to enhance autonomous navigation in off-road environments. |
Peng Jiang; Philip Osteen; Maggie Wigness; Srikanth Saripalli; | arxiv-cs.CV | 2020-11-17 |
| 469 | Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce stochastic segmentation networks (SSNs), an efficient probabilistic method for modelling aleatoric uncertainty with any image segmentation network architecture. |
MIGUEL MONTEIRO et. al. | nips | 2020-11-17 |
| 470 | Contrastive Registration for Unsupervised Medical Image Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a novel optimisation model framed into a new CNN-based contrastive registration architecture for unsupervised medical image segmentation. |
Lihao Liu; Angelica I Aviles-Rivero; Carola-Bibiane Schönlieb; | arxiv-cs.CV | 2020-11-17 |
| 471 | RANet: Region Attention Network For Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce the \emph{Region Attention Network} (RANet), a novel attention network for modeling the relationship between object regions. |
Dingguo Shen; Yuanfeng Ji; Ping Li; Yi Wang; Di Lin; | nips | 2020-11-17 |
| 472 | Consistent Structural Relation Learning For Zero-Shot Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a Consistent Structural Relation Learning (CSRL) approach to constrain the generating of unseen visual features by exploiting the structural relations between seen and unseen categories. |
Peike Li; Yunchao Wei; Yi Yang; | nips | 2020-11-17 |
| 473 | Discover, Hallucinate, And Adapt: Open Compound Domain Adaptation For Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate open compound domain adaptation (OCDA), which deals with mixed and novel situations at the same time, for semantic segmentation. |
KwanYong Park; Sanghyun Woo; Inkyu Shin; In So Kweon; | nips | 2020-11-17 |
| 474 | High-level Prior-based Loss Functions For Medical Image Segmentation: A Survey IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this survey, we focus on high level prior, embedded at the loss function level. |
Rosana El Jurdi; Caroline Petitjean; Paul Honeine; Veronika Cheplygina; Fahed Abdallah; | arxiv-cs.CV | 2020-11-16 |
| 475 | LULC Classification By Semantic Segmentation Of Satellite Images Using FastFCN IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose FastFCN to be both faster and more accurate automated method than other existing methods for LULC classification. |
Md. Saif Hassan Onim; Aiman Rafeed Ehtesham; Amreen Anbar; A. K. M. Nazrul Islam; A. K. M. Mahbubur Rahman; | arxiv-cs.CV | 2020-11-13 |
| 476 | ROLL: Visual Self-Supervised Reinforcement Learning With Object Reasoning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we improve upon previous visual self-supervised RL by incorporating object-level reasoning and occlusion reasoning. |
Yufei Wang; Gautham Narayan Narasimhan; Xingyu Lin; Brian Okorn; David Held; | arxiv-cs.LG | 2020-11-13 |
| 477 | Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an efficient and robust RGB-D segmentation approach that can be optimized to a high degree using NVIDIA TensorRT and, thus, is well suited as a common initial processing step in a complex system for scene analysis on mobile robots. |
Daniel Seichter; Mona Köhler; Benjamin Lewandowski; Tim Wengefeld; Horst-Michael Gross; | arxiv-cs.CV | 2020-11-13 |
| 478 | Form2Seq : A Framework For Higher-Order Form Structure Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate this, we propose Form2Seq, a novel sequence-to-sequence (Seq2Seq) inspired framework for structure extraction using text, with a specific focus on forms, which leverages relative spatial arrangement of structures. |
Milan Aggarwal; Hiresh Gupta; Mausoom Sarkar; Balaji Krishnamurthy; | emnlp | 2020-11-12 |
| 479 | Learning To Segment Dynamic Objects Using SLAM Outliers IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a method to automatically learn to segment dynamic objects using SLAM outliers. We also propose a new stereo dataset and new metrics to evaluate SLAM robustness. |
Adrian Bojko; Romain Dupont; Mohamed Tamaazousti; Hervé Le Borgne; |