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
| Title | Author(s) | Highlight | Category | Date | |
|---|---|---|---|---|---|
| 1 | GAN Mask R-CNN:Instance Semantic Segmentation Benefits From Generativeadversarial Networks | QUANG H. LE et. al. | We show this design outperforms the baseline when trying on, without extra settings, several different domains: cellphone recycling, autonomous driving, large-scale object detection, and medical glands. | CS.arxiv | 2020-10-26 |
| 2 | A Centroid Loss For Weakly Supervised Semantic Segmentation In Quality Control And Inspection Application | KAI YAO et. al. | In this paper, a semantic segmentation solution is proposed for two scenes. | CS.arxiv | 2020-10-26 |
| 3 | Lane Detection In Complex Scenes Based On End-to-end Neural Network | WENBO LIU et. al. | So we combine the advantages of spatial convolution in spatial information processing and the efficiency of ERFNet in semantic segmentation, propose an end-to-end network to lane detection in a variety of complex scenes. | CS.arxiv | 2020-10-26 |
| 4 | Global Image Segmentation Process Using Machine Learning Algorithm & Convolution Neural Network Method For Self- Driving Vehicles | TIRUMALAPUDI RAVITEJA et. al. | We proposed this image segmentation method planning to standard and further the development of state-of-the art methods for visual inspection system understanding. | CS.arxiv | 2020-10-25 |
| 5 | Weakly-Supervised Amodal Instance Segmentation With Compositional Priors | YIHONG SUN et. al. | In this paper, we present a neural network architecture that is capable of amodal perception, when weakly supervised with standard (inmodal) bounding box annotations. | CS.arxiv | 2020-10-25 |
| 6 | Coherent Loss: A Generic Framework For Stable Video Segmentation | MINGYANG QIAN et. al. | In particular, we propose a Coherent Loss with a generic framework to enhance the performance of a neural network against jittering artifacts, which combines with high accuracy and high consistency. | CS.arxiv | 2020-10-25 |
| 7 | Scribble-based Weakly Supervised Deep Learning For Road Surface Extraction From Remote Sensing Images | YAO WEI et. al. | To propagate semantic information from sparse scribbles to unlabeled pixels, we introduce a road label propagation algorithm which considers both the buffer-based properties of road networks and the color and spatial information of super-pixels. | CS.arxiv | 2020-10-25 |
| 8 | A Teacher-Student Framework For Semi-supervised Medical Image Segmentation From Mixed Supervision | LIYAN SUN et. al. | Observing the geometrical relation of an organ and its inner lesions in most cases, we propose a hierarchical organ-to-lesion (O2L) attention module in a teacher segmentor to produce pseudo-labels. | CS.arxiv | 2020-10-23 |
| 9 | Delving Into The Cyclic Mechanism In Semi-supervised Video Object Segmentation | YUXI LI et. al. | In this paper, we address several inadequacies of current video object segmentation pipelines. | CS.arxiv | 2020-10-23 |
| 10 | Domain Adaptation In LiDAR Semantic Segmentation | INIGO ALONSO et. al. | Besides, we propose a learning-based approach that aligns the distribution of the semantic classes of the target domain to the source domain. | CS.arxiv | 2020-10-23 |
| 11 | Learning To Sort Image Sequences Via Accumulated Temporal Differences | GAGAN KANOJIA et. al. | In this work, we tackle the problem of temporally sequencing the unordered set of images of a dynamic scene captured with a hand-held camera. | CS.arxiv | 2020-10-22 |
| 12 | Task-Adaptive Feature Transformer For Few-Shot Segmentation | JUN SEO et. al. | In this paper, we propose a learnable module for few-shot segmentation, the task-adaptive feature transformer (TAFT). | CS.arxiv | 2020-10-22 |
| 13 | UAV LiDAR Point Cloud Segmentation Of A Stack Interchange With Deep Neural Networks | WEIKAI TAN et. al. | An end-to-end supervised 3D deep learning framework was proposed to classify the point clouds. | CS.arxiv | 2020-10-21 |
| 14 | What Is Wrong With Continual Learning In Medical Image Segmentation? | CAMILA GONZALEZ et. al. | In this work, we propose an evaluation framework that addresses both concerns, and introduce a fair multi-model benchmark. | CS.arxiv | 2020-10-21 |
| 15 | Dense Dual-Path Network For Real-time Semantic Segmentation | XINNENG YANG et. al. | In this paper, we introduce a novel Dense Dual-Path Network (DDPNet) for real-time semantic segmentation under resource constraints. | CS.arxiv | 2020-10-21 |
| 16 | RigidFusion: Robot Localisation And Mapping In Environments With Large Dynamic Rigid Objects | RAN LONG et. al. | This work presents a novel approach to simultaneously track a robot with respect to multiple rigid entities, including the environment and additional dynamic objects in a scene. | CS.arxiv | 2020-10-21 |
| 17 | Efficient Scale-Permuted Backbone With Learned Resource Distribution | XIANZHI DU et. al. | In this work, we propose a simple technique to combine efficient operations and compound scaling with a previously learned scale-permuted architecture. | CS.arxiv | 2020-10-21 |
| 18 | 2nd Place Solution To Instance Segmentation Of IJCAI 3D AI Challenge 2020 | KAI JIANG et. al. | 2nd Place Solution To Instance Segmentation Of IJCAI 3D AI Challenge 2020 | CS.arxiv | 2020-10-21 |
| 19 | TTPLA: An Aerial-Image Dataset For Detection And Segmentation Of Transmission Towers And Power Lines | RABAB ABDELFATTAH et. al. | In this paper we collect and release a new TT/PL Aerial-image (TTPLA) dataset, consisting of 1,100 images with the resolution of 3,840$\times$2,160 pixels, as well as manually labeled 8,987 instances of TTs and PLs. | CS.arxiv | 2020-10-20 |
| 20 | Color Image Segmentation Metrics | MAJID HAROUNI et. al. | This entry presents the state of the art of quantitative evaluation metrics for color image segmentation methods by performing an analytical and comparative review of the measures. | CS.arxiv | 2020-10-19 |
| 21 | Noisy-LSTM: Improving Temporal Awareness For Video Semantic Segmentation | BOWEN WANG et. al. | This paper presents a new model named Noisy-LSTM, which is trainable in an end-to-end manner, with convolutional LSTMs (ConvLSTMs) to leverage the temporal coherency in video frames. | CS.arxiv | 2020-10-19 |
| 22 | The STDyn-SLAM: A Stereo Vision And Semantic Segmentation Approach For SLAM In Dynamic Outdoor Environments | DANIELA ESPARZA et. al. | This work presents the STDyn-SLAM an image feature-based SLAM system working on dynamic environments using a series of sub-systems, like optic flow, orb features extraction, visual odometry, and convolutional neural networks to discern moving objects in the scene. | CS.arxiv | 2020-10-19 |
| 23 | Weakly-supervised Learning For Catheter Segmentation In 3D Frustum Ultrasound | HONGXU YANG et. al. | In this paper, we propose a novel Frustum ultrasound based catheter segmentation method. | CS.arxiv | 2020-10-19 |
| 24 | PseudoSeg: Designing Pseudo Labels For Semantic Segmentation | YULIANG ZOU et. al. | To address this problem, we present a simple and novel re-design of pseudo-labeling to generate well-calibrated structured pseudo labels for training with unlabeled or weakly-labeled data. | CS.arxiv | 2020-10-19 |
| 25 | Semantic-Guided Inpainting Network For Complex Urban Scenes Manipulation | PIERFRANCESCO ARDINO et. al. | In this work, we propose a novel deep learning model to alter a complex urban scene by removing a user-specified portion of the image and coherently inserting a new object (e.g. car or pedestrian) in that scene. | CS.arxiv | 2020-10-19 |
| 26 | DEAL: Difficulty-aware Active Learning For Semantic Segmentation | SHUAI XIE et. al. | To deal with this problem, we propose a semantic Difficulty-awarE Active Learning (DEAL) network composed of two branches: the common segmentation branch and the semantic difficulty branch. | CS.arxiv | 2020-10-16 |
| 27 | In Depth Bayesian Semantic Scene Completion | DAVID GILLSJÖ et. al. | We show on the MNIST dataset that the Bayesian approach performs equal or better to the standard CNN when processing digits unseen in the training phase when looking at accuracy, precision and recall. | CS.arxiv | 2020-10-16 |
| 28 | Automated Iterative Training Of Convolutional Neural Networks For Tree Skeleton Segmentation | KEENAN GRANLAND et. al. | This paper describes a new iterative training method: Automating-the-loop. | CS.arxiv | 2020-10-16 |
| 29 | Human Perception-based Evaluation Criterion For Ultra-high Resolution Cell Membrane Segmentation | RUOHUA SHI et. al. | During the analysis process of the U-RISC, we found that the current popular segmentation evaluation criteria are inconsistent with human perception. In order to solve these two problems, this paper first proposes an Ultra-high Resolution Image Segmentation dataset for the Cell membrane, called U-RISC, the largest annotated Electron Microscopy (EM) dataset for the Cell membrane with multiple iterative annotations and uncompressed high-resolution raw data. | CS.arxiv | 2020-10-16 |
| 30 | Zoom-CAM: Generating Fine-grained Pixel Annotations From Image Labels | XIANGWEI SHI et. al. | We propose Zoom-CAM: going beyond the last lowest resolution layer by integrating the importance maps over all activations in intermediate layers. | CS.arxiv | 2020-10-16 |
| 31 | Ensembling Low Precision Models For Binary Biomedical Image Segmentation | TIANYU MA et. al. | In this paper, we aim to leverage this asymmetry and train a diverse ensemble of models with very high recall, while sacrificing their precision. | CS.arxiv | 2020-10-16 |
| 32 | Empty Cities: A Dynamic-Object-Invariant Space For Visual SLAM | BERTA BESCOS et. al. | In this paper we present a data-driven approach to obtain the static image of a scene, eliminating dynamic objects that might have been present at the time of traversing the scene with a camera. | CS.arxiv | 2020-10-15 |
| 33 | HS-ResNet: Hierarchical-Split Block On Convolutional Neural Network | PENGCHENG YUAN et. al. | In this work, we present a common backbone based on Hierarchical-Split block for tasks: image classification, object detection, instance segmentation and semantic image segmentation/parsing. | CS.arxiv | 2020-10-15 |
| 34 | Video Object Segmentation With Adaptive Feature Bank And Uncertain-Region Refinement | YONGQING LIANG et. al. | We propose a new matching-based framework for semi-supervised video object segmentation (VOS). | CS.arxiv | 2020-10-15 |
| 35 | Auto Seg-Loss: Searching Metric Surrogates For Semantic Segmentation | HAO LI et. al. | We propose a general framework for searching surrogate losses for mainstream semantic segmentation metrics. | CS.arxiv | 2020-10-15 |
| 36 | Semi-Supervised Semantic Segmentation In Earth Observation: The MiniFrance Suite, Dataset Analysis And Multi-task Network Study | JAVIERA CASTILLO-NAVARRO et. al. | We introduce a novel large-scale dataset for semi-supervised semantic segmentation in Earth Observation, the MiniFrance suite. | CS.arxiv | 2020-10-15 |
| 37 | DynaSLAM II: Tightly-Coupled Multi-Object Tracking And SLAM | BERTA BESCOS et. al. | We present in this paper DynaSLAM II, a visual SLAM system for stereo and RGB-D configurations that tightly integrates the multi-object tracking capability. | CS.arxiv | 2020-10-15 |
| 38 | Semantic Segmentation For Partially Occluded Apple Trees Based On Deep Learning | ZIJUE CHEN et. al. | In this work, we apply two state-of-the-art supervised learning models U-Net and DeepLabv3, and a conditional Generative Adversarial Network Pix2Pix (with and without the discriminator) to segment partially occluded 2D-open-V apple trees. | CS.arxiv | 2020-10-14 |
| 39 | PP-LinkNet: Improving Semantic Segmentation Of High Resolution Satellite Imagery With Multi-stage Training | AN TRAN et. al. | In this paper, we propose a two-stage transfer learning technique to improve robustness of semantic segmentation for satellite images that leverages noisy pseudo ground truth masks obtained automatically (without human labor) from crowd-sourced OpenStreetMap (OSM) data. | CS.arxiv | 2020-10-14 |
| 40 | Collaborative Video Object Segmentation By Multi-Scale Foreground-Background Integration | ZONGXIN YANG et. al. | Thus, we propose a Collaborative video object segmentation by Foreground-Background Integration (CFBI) approach. | CS.arxiv | 2020-10-13 |
| 41 | Land Cover Semantic Segmentation Using ResUNet | VASILIS POLLATOS et. al. | In this paper we present our work on developing an automated system for land cover classification. We created a dataset from scratch covering this particular area. | CS.arxiv | 2020-10-13 |
| 42 | Exploring Efficient Volumetric Medical Image Segmentation Using 2.5D Method: An Empirical Study | YICHI ZHANG et. al. | In this paper, we aim to present a review of the latest developments of 2.5D methods for volumetric medical image segmentation. | CS.arxiv | 2020-10-13 |
| 43 | DoFE: Domain-oriented Feature Embedding For Generalizable Fundus Image Segmentation On Unseen Datasets | SHUJUN WANG et. al. | To alleviate this issue, we present a novel Domain-oriented Feature Embedding (DoFE) framework to improve the generalization ability of CNNs on unseen target domains by exploring the knowledge from multiple source domains. | CS.arxiv | 2020-10-13 |
| 44 | Deep Structural Contour Detection | RUOXI DENG et. al. | In this work, we aim to develop a high-performance contour detection system. | CS.mm | 2020-10-12 |
| 45 | Cap2Seg: Inferring Semantic And Spatial Context From Captions For Zero-Shot Image Segmentation | GUIYU TIAN et. al. | In this work we describe Cap2Seg, a novel solution of zero-shot image segmentation that harnesses accompanying image captions for intelligently inferring spatial and semantic context for the zero-shot image segmentation task. | CS.mm | 2020-10-12 |
| 46 | Dual Temporal Memory Network For Efficient Video Object Segmentation | KAIHUA ZHANG et. al. | We present an end-to-end network which stores short- and long-term video sequence information preceding the current frame as the temporal memories to address the temporal modeling in VOS. | CS.mm | 2020-10-12 |
| 47 | Integrating Semantic Segmentation And Retinex Model For Low-Light Image Enhancement | MINHAO FAN et. al. | We propose an enhancement pipeline with three parts that effectively utilize the semantic layer information. | CS.mm | 2020-10-12 |
| 48 | Learning Deep Multimodal Feature Representation With Asymmetric Multi-layer Fusion | YIKAI WANG et. al. | We propose a compact and effective framework to fuse multimodal features at multiple layers in a single network. | CS.mm | 2020-10-12 |
| 49 | Meta Parsing Networks: Towards Generalized Few-shot Scene Parsing With Adaptive Metric Learning | PEIKE LI et. al. | In this work, we advance this few-shot segmentation paradigm towards a more challenging yet general scenario, i.e., Generalized Few-shot Scene Parsing (GFSP). | CS.mm | 2020-10-12 |
| 50 | CF-SIS: Semantic-Instance Segmentation Of 3D Point Clouds By Context Fusion With Self-Attention | XIN WEN et. al. | To address the above two issues, we propose a novel network of feature context fusion for SIS task, named CF-SIS. | CS.mm | 2020-10-12 |
| 51 | Deep Relationship Analysis In Video With Multimodal Feature Fusion | FAN YU et. al. | In this paper, we propose a novel multimodal feature fusion method based on scene segmentation to detect the relationships between entities in a long duration video. | CS.mm | 2020-10-12 |
| 52 | March On Data Imperfections: Domain Division And Domain Generalization For Semantic Segmentation | HAI XU et. al. | In contrast to previous works, we present a novel model-agnostic training optimization algorithm which has two prominent components: Domain Division and Domain Generalization. | CS.mm | 2020-10-12 |
| 53 | DMVOS: Discriminative Matching For Real-time Video Object Segmentation | PEISONG WEN et. al. | In this work, we propose Discriminative Matching for real-time Video Object Segmentation (DMVOS), a real-time VOS framework with high-accuracy to fill this gap. | CS.mm | 2020-10-12 |
| 54 | Increasing The Robustness Of Semantic Segmentation Models With Painting-by-Numbers | CHRISTOPH KAMANN et. al. | We present a new training schema that increases this shape bias. | CS.arxiv | 2020-10-12 |
| 55 | Context-aware Feature Generation For Zero-shot Semantic Segmentation | ZHANGXUAN GU et. al. | In this paper, we propose a novel context-aware feature generation method for zero-shot segmentation named CaGNet. | CS.mm | 2020-10-12 |
| 56 | Fully Automatic Wound Segmentation With Deep Convolutional Neural Networks | CHUANBO WANG et. al. | This manuscript proposes a novel convolutional framework based on MobileNetV2 and connected component labelling to segment wound regions from natural images. We build an annotated wound image dataset consisting of 1,109 foot ulcer images from 889 patients to train and test the deep learning models. | CS.arxiv | 2020-10-12 |
| 57 | Dynamic Extension Nets For Few-shot Semantic Segmentation | LIZHAO LIU et. al. | To address the above issues, we propose a Dynamic Extension Network (DENet) in which we dynamically construct and maintain a classifier for the novel class by leveraging the knowledge from the base classes and the information from novel data. | CS.mm | 2020-10-12 |
| 58 | Generalized Few-Shot Semantic Segmentation | ZHUOTAO TIAN et. al. | In this paper, we introduce a new benchmark, called Generalized Few-Shot Semantic Segmentation (GFS-Seg), to analyze the generalization ability of segmentation models to simultaneously recognize novel categories with very few examples as well as base categories with sufficient examples. | CS.arxiv | 2020-10-11 |
| 59 | H2O-Net: Self-Supervised Flood Segmentation Via Adversarial Domain Adaptation And Label Refinement | PERI AKIVA et. al. | This work presents H2O-Network, a self supervised deep learning method to segment floods from satellites and aerial imagery by bridging domain gap between low and high latency satellite and coarse-to-fine label refinement. | CS.arxiv | 2020-10-11 |
| 60 | Hybrid Sequence To Sequence Model For Video Object Segmentation | FATEMEH AZIMI et. al. | In this work, we study an RNN-based architecture and address some of these issues by proposing a hybrid sequence-to-sequence architecture named HS2S, utilizing a hybrid mask propagation strategy that allows incorporating the information obtained from correspondence matching. | CS.arxiv | 2020-10-10 |
| 61 | Selective Information Passing For MR/CT Image Segmentation | QIKUI ZHU et. al. | In this paper, to adaptively select useful information to pass through those skip connections, we propose a novel 3D network with self-supervised function, named selective information passing network (SIP-Net). | CS.arxiv | 2020-10-10 |
| 62 | HCNet: Hierarchical Context Network For Semantic Segmentation | YANWEN CHONG et. al. | In order to solve the above problem, we propose a hierarchical context network to differentially model homogeneous pixels with strong correlations and heterogeneous pixels with weak correlations. | CS.arxiv | 2020-10-10 |
| 63 | Deep Learning Superpixel Semantic Segmentation With Transparent Initialization And Sparse Encoder | ZHIWEI XU et. al. | As superpixel is a popular and effective auxiliary to preserve object edges, in this paper, we jointly learn semantic segmentation with trainable superpixels. | CS.arxiv | 2020-10-09 |
| 64 | Vision-Based Object Recognition In Indoor Environments Using Topologically Persistent Features | EKTA U. SAMANI et. al. | In this letter, we propose the use of topologically persistent features, which rely on the shape information of the objects, to address this challenge. For performance evaluation, in addition to a widely-used shape dataset, we collect a new dataset comprising scene images from two different environments, namely, a living room and a mock warehouse. | CS.arxiv | 2020-10-07 |
| 65 | Deep Tiered Image Segmentation ForDetecting Internal Ice Layers In Radar Imagery | YUCHEN WANG et. al. | In this paper, we propose a novel deep neural network-based model for solving a general class of tiered segmentation problems. | CS.arxiv | 2020-10-07 |
| 66 | Vec2Instance: Parameterization For Deep Instance Segmentation | N. LAKMAL DESHAPRIYA et. al. | In this paper, we describe a new deep convolutional neural network architecture called Vec2Instance for instance segmentation. | CS.arxiv | 2020-10-06 |
| 67 | Depth-wise Layering Of 3d Images Using Dense Depth Maps: A Threshold Based Approach | SEYEDSAEID MIRKAMALI et. al. | The technique employs a thresholding approach to segment rows of the dense depth map into smaller partitions called Line-Segments in this paper. | CS.arxiv | 2020-10-05 |
| 68 | MetaBox+: A New Region Based Active Learning Method For Semantic Segmentation Using Priority Maps | PASCAL COLLING et. al. | We present a novel region based active learning method for semantic image segmentation, called MetaBox+. | CS.arxiv | 2020-10-05 |
| 69 | CO2: Consistent Contrast For Unsupervised Visual Representation Learning | CHEN WEI et. al. | To address this issue, inspired by consistency regularization in semi-supervised learning on unlabeled data, we propose Consistent Contrast (CO2), which introduces a consistency regularization term into the current contrastive learning framework. | CS.arxiv | 2020-10-05 |
| 70 | Collaboratively Boosting Data-driven Deep Learning And Knowledge-guided Ontological Reasoning For Semantic Segmentation Of Remote Sensing Imagery | YANSHENG LI et. al. | To remedy the aforementioned critical limitation of DSSN, this paper proposes a collaboratively boosting framework (CBF) to combine data-driven deep learning module and knowledge-guided ontological reasoning module in an iterative way. | CS.arxiv | 2020-10-05 |
| 71 | Semi-Supervised Learning For Multi-Task Scene Understanding By Neural Graph Consensus | MARIUS LEORDEANU et. al. | We address the challenging problem of semi-supervised learning in the context of multiple visual interpretations of the world by finding consensus in a graph of neural networks. | CS.arxiv | 2020-10-02 |
| 72 | AIM 2020 Challenge On Image Extreme Inpainting | EVANGELOS NTAVELIS et. al. | This paper reviews the AIM 2020 challenge on extreme image inpainting. | CS.arxiv | 2020-10-02 |
| 73 | Linguistic Structure Guided Context Modeling For Referring Image Segmentation | TIANRUI HUI et. al. | To tackle this problem, we propose a gather-propagate-distribute scheme to model multimodal context by cross-modal interaction and implement this scheme as a novel Linguistic Structure guided Context Modeling (LSCM) module. | CS.arxiv | 2020-10-01 |
| 74 | Referring Image Segmentation Via Cross-Modal Progressive Comprehension | SHAOFEI HUANG et. al. | In this paper, we propose a Cross-Modal Progressive Comprehension (CMPC) module and a Text-Guided Feature Exchange (TGFE) module to effectively address the challenging task. | CS.arxiv | 2020-10-01 |
| 75 | RefVOS: A Closer Look At Referring Expressions For Video Object Segmentation | MIRIAM BELLVER et. al. | Our work argues that existing benchmarks used for this task are mainly composed of trivial cases, in which referents can be identified with simple phrases. | CS.arxiv | 2020-10-01 |
| 76 | Deep Learning For Earth Image Segmentation Based On Imperfect Polyline Labels With Annotation Errors | ZHE JIANG et. al. | To fill the gap, this paper proposes a generic learning framework based on the EM algorithm to update deep learning model parameters and infer hidden true label locations simultaneously. | CS.arxiv | 2020-10-01 |
| 77 | Towards Adaptive Semantic Segmentation By Progressive Feature Refinement | BIN ZHANG et. al. | In this paper, we propose an innovative progressive feature refinement framework, along with domain adversarial learning to boost the transferability of segmentation networks. | CS.arxiv | 2020-09-30 |
| 78 | The Utility Of Decorrelating Colour Spaces In Vector Quantised Variational Autoencoders | ARASH AKBARINIA et. al. | In this article, we propose colour space conversion, a simple quasi-unsupervised task, to enforce a network learning structured representations. | CS.arxiv | 2020-09-30 |
| 79 | Realistic Image Normalization For Multi-Domain Segmentation | PIERRE-LUC DELISLE et. al. | This paper proposes to revisit the conventional image normalization approach by instead learning a common normalizing function across multiple datasets. | CS.arxiv | 2020-09-29 |
| 80 | Incomplete Utterance Rewriting As Semantic Segmentation | QIAN LIU et. al. | In this paper, we present a novel and extensive approach, which formulates it as a semantic segmentation task. | CS.arxiv | 2020-09-28 |
| 81 | A Survey On Deep Learning Methods For Semantic Image Segmentation In Real-Time | GEORGIOS TAKOS | This work provides a comprehensive analysis of state-of-the-art deep learning architectures in image segmentation and, more importantly, an extensive list of techniques to achieve fast inference and computational efficiency. | CS.arxiv | 2020-09-27 |
| 82 | Unsupervised Model Adaptation For Continual Semantic Segmentation | SERBAN STAN et. al. | We develop an algorithm for adapting a semantic segmentation model that is trained using a labeled source domain to generalize well in an unlabeled target domain. | CS.arxiv | 2020-09-26 |
| 83 | Causal Intervention For Weakly-Supervised Semantic Segmentation | DONG ZHANG et. al. | We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). | CS.arxiv | 2020-09-26 |
| 84 | SemanticVoxels: Sequential Fusion For 3D Pedestrian Detection Using LiDAR Point Cloud And Semantic Segmentation | JUNCONG FEI et. al. | In this paper, we propose a generalization of PointPainting to be able to apply fusion at different levels. | CS.arxiv | 2020-09-25 |
| 85 | From Pixel To Patch: Synthesize Context-aware Features For Zero-shot Semantic Segmentation | ZHANGXUAN GU et. al. | In this paper, we propose a novel Context-aware feature Generation Network (CaGNet), which can synthesize context-aware pixel-wise visual features for unseen categories based on category-level semantic representations and pixel-wise contextual information. | CS.arxiv | 2020-09-25 |
| 86 | Going To Extremes: Weakly Supervised Medical Image Segmentation | HOLGER R ROTH et. al. | Medical image annotation is a major hurdle for developing precise and robust machine learning models. | CS.arxiv | 2020-09-24 |
| 87 | Cloud Cover Nowcasting With Deep Learning | LÉA BERTHOMIER et. al. | In this paper, we focus on cloud cover nowcasting, which has various application areas such as satellite shots optimisation and photovoltaic energy production forecast. | CS.arxiv | 2020-09-24 |
| 88 | Local Context Attention For Salient Object Segmentation | JING TAN et. al. | Based on this priori, we propose a novel Local Context Attention Network (LCANet) to generate locally reinforcement feature maps in a uniform representational architecture. | CS.arxiv | 2020-09-24 |
| 89 | Interactive Learning For Semantic Segmentation In Earth Observation | GASTON LENCZNER et. al. | Therefore, we propose to interactively refine them within a framework named DISCA (Deep Image Segmentation with Continual Adaptation). | CS.arxiv | 2020-09-23 |
| 90 | BoMuDA: Boundless Multi-Source Domain Adaptive Segmentation In Unconstrained Environments | DIVYA KOTHANDARAMAN et. al. | We present an unsupervised multi-source domain adaptive semantic segmentation approach in unstructured and unconstrained traffic environments. | CS.arxiv | 2020-09-22 |
| 91 | Improving Point Cloud Semantic Segmentation By Learning 3D Object Proposal Generation | OZAN UNAL et. al. | We propose a novel Detection Aware 3D Semantic Segmentation (DASS) framework that explicitly leverages localization features from an auxiliary 3D object detection task. | CS.arxiv | 2020-09-22 |
| 92 | Angular Luminance For Material Segmentation | JIA XUE et. al. | We utilize per-pixel {\it angular luminance distributions} as a key feature in discriminating the material of the surface. | CS.arxiv | 2020-09-22 |
| 93 | Discriminative Segmentation Tracking Using Dual Memory Banks | FEI XIE et. al. | To overcome these limitations, this work presents a novel discriminative segmentation tracking architecture equipped with dual memory banks, i.e., appearance memory bank and spatial memory bank. | CS.arxiv | 2020-09-21 |
| 94 | Semi-supervised Semantic Segmentation Of Prostate And Organs-at-Risk On 3D Pelvic CT Images | ZHUANGZHUANG ZHANG et. al. | Taking automated segmentation of OARs as a case study, we developed a novel semi-supervised adversarial deep learning approach to support medical image data processing and modeling where training data may be insufficient. | CS.arxiv | 2020-09-20 |
| 95 | Synthetic Convolutional Features For Improved Semantic Segmentation | YANG HE et. al. | Therefore, we suggest to generate intermediate convolutional features and propose the first synthesis approach that is catered to such intermediate convolutional features. | CS.arxiv | 2020-09-18 |
| 96 | Prepare For The Worst: Generalizing Across Domain Shifts With Adversarial Batch Normalization | MANLI SHU et. al. | We adapt adversarial training by adversarially perturbing these feature statistics, rather than image pixels, to produce models that are robust to domain shift. | CS.arxiv | 2020-09-18 |
| 97 | Multi-Resolution Graph Neural Network For Large-Scale Pointcloud Segmentation | LIUYUE XIE et. al. | In this paper, we propose a multi-resolution deep-learning architecture to semantically segment dense large-scale pointclouds. | CS.arxiv | 2020-09-18 |
| 98 | TopNet: Topology Preserving Metric Learning For Vessel Tree Reconstruction And Labelling | DEEPAK KESHWANI et. al. | To tackle this, we propose a novel multi-task deep learning architecture for vessel tree reconstruction. | CS.arxiv | 2020-09-18 |
| 99 | Consistency Regularization With High-dimensional Non-adversarial Source-guided Perturbation For Unsupervised Domain Adaptation In Segmentation | KAIHONG WANG et. al. | In this paper, we propose a bidirectional style-induced domain adaptation method, called BiSIDA, that employs consistency regularization to efficiently exploit information from the unlabeled target domain dataset, requiring only a simple neural style transfer model. | CS.arxiv | 2020-09-17 |
| 101 | UXNet: Searching Multi-level Feature Aggregation For 3D Medical Image Segmentation | YUANFENG JI et. al. | Unlike the recent neural architecture search (NAS) methods that typically searched the optimal operators in each network layer, but missed a good strategy to search for feature aggregations, this paper proposes a novel NAS method for 3D medical image segmentation, named UXNet, which searches both the scale-wise feature aggregation strategies as well as the block-wise operators in the encoder-decoder network. | CS.arxiv | 2020-09-16 |
| 102 | Optimal Use Of Multi-spectral Satellite Data With Convolutional Neural Networks | SAGAR VAZE et. al. | In this paper, we compare different methods of leveraging multi-band information with CNNs, demonstrating the performance of all compared methods on the task of semantic segmentation of agricultural vegetation (vineyards). | CS.arxiv | 2020-09-15 |
| 103 | Multi-scale Attention U-Net (MsAUNet): A Modified U-Net Architecture For Scene Segmentation | SOHAM CHATTOPADHYAY et. al. | In this paper, we propose a novel multi-scale attention network for scene segmentation purposes by using the rich contextual information from an image. | CS.arxiv | 2020-09-15 |
| 104 | DAER To Reject Seeds With Dual-loss Additional Error Regression | STEPHAN J. LEMMER et. al. | With these challenges in mind, we propose a novel training method and evaluation metrics for the seed rejection problem. We hence propose the novel problem of seed rejection—determining whether to reject a seed based on expected degradation relative to the gold-standard. | CS.arxiv | 2020-09-15 |
| 105 | EfficientSeg: An Efficient Semantic Segmentation Network | VAHIT BUGRA YESILKAYNAK et. al. | Thus, we introduce EfficientSeg architecture, a modified and scalable version of U-Net, which can be efficiently trained despite its depth. | CS.arxiv | 2020-09-14 |
| 106 | SML: Semantic Meta-learning For Few-shot Semantic Segmentation | AYYAPPA KUMAR PAMBALA et. al. | In this work, we propose a novel meta-learning framework, Semantic Meta-Learning (SML) which incorporates class level semantic descriptions in the generated prototypes for this problem. | CS.arxiv | 2020-09-14 |
| 107 | RelativeNAS: Relative Neural Architecture Search Via Slow-Fast Learning | HAO TAN et. al. | To benefit from the merits while overcoming the deficiencies of both, this work proposes a novel NAS method, RelativeNAS. | CS.arxiv | 2020-09-14 |
| 108 | Semantic Segmentation Of Surface From Lidar Point Cloud | ARITRA MUKHERJEE et. al. | The methodology presented proposes a fast algorithm that can be used to extract semantically labelled surface segments from the cloud, in real time, for direct navigational use or higher level contextual scene reconstruction. | CS.arxiv | 2020-09-13 |
| 109 | GINet: Graph Interaction Network For Scene Parsing | TIANYI WU et. al. | In this work, we explore how to incorporate the linguistic knowledge to promote context reasoning over image regions by proposing a Graph Interaction unit (GI unit) and a Semantic Context Loss (SC-loss). | CS.arxiv | 2020-09-13 |
| 110 | Multi-Spectral Image Synthesis For Crop/Weed Segmentation In Precision Farming | MULHAM FAWAKHERJI et. al. | In this work, we propose an alternative solution with respect to the common data augmentation techniques, applying it to the fundamental problem of crop/weed segmentation in precision farming. | CS.arxiv | 2020-09-12 |
| 111 | Hierarchical Roofline Performance Analysis For Deep Learning Applications | YUNSONG WANG et. al. | This paper presents a practical methodology for collecting performance data necessary to conduct hierarchical Roofline analysis on NVIDIA GPUs. | CS.arxiv | 2020-09-11 |
| 112 | Variance Loss: A Confidence-Based Reweighting Strategy For Coarse Semantic Segmentation | JINGCHAO LIU et. al. | Though they are usually used as a supplement to the finely-labeled ones, in this paper, we attempt to train a model only using these coarse annotations, and improve the model performance with a noise-robust reweighting strategy. | CS.arxiv | 2020-09-10 |
| 113 | Semi-supervised Medical Image Segmentation Through Dual-task Consistency | XIANGDE LUO et. al. | To answer this question, we propose a novel dual-task-consistency semi-supervised framework for the first time. | CS.arxiv | 2020-09-09 |
| 114 | Towards Fine-grained Large Object Segmentation 1st Place Solution To 3D AI Challenge 2020 — Instance Segmentation Track | ZEHUI CHEN et. al. | This technical report introduces our solutions of Team ‘FineGrainedSeg’ for Instance Segmentation track in 3D AI Challenge 2020. | CS.arxiv | 2020-09-09 |
| 115 | Towards Semantic Segmentation Of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks And Challenges | QINGYONG HU et. al. | In this paper, we present an urban-scale photogrammetric point cloud dataset with nearly three billion richly annotated points, which is five times the number of labeled points than the existing largest point cloud dataset. | CS.arxiv | 2020-09-07 |
| 116 | Visual Object Tracking By Segmentation With Graph Convolutional Network | BO JIANG et. al. | In this paper, we propose to utilize graph convolutional network (GCN) model for superpixel based object tracking. | CS.arxiv | 2020-09-05 |
| 117 | SCG-Net: Self-Constructing Graph Neural Networks For Semantic Segmentation | QINGHUI LIU et. al. | Inspired by recent work on graph neural networks, we propose the Self-Constructing Graph (SCG) module that learns a long-range dependency graph directly from the image and uses it to propagate contextual information efficiently to improve semantic segmentation. | CS.arxiv | 2020-09-03 |
| 118 | DESC: Domain Adaptation For Depth Estimation Via Semantic Consistency | ADRIAN LOPEZ-RODRIGUEZ et. al. | Instead, in this paper, we propose a domain adaptation approach to train a monocular depth estimation model using a fully-annotated source dataset and a non-annotated target dataset. | CS.arxiv | 2020-09-03 |
| 119 | On The Structures Of Representation For The Robustness Of Semantic Segmentation To Input Corruption | CHARLES LEHMAN et. al. | In this paper, we provide analysis comparing the structures learned as a result of optimization objectives that use Softmax, IBE, and Sigmoid in order to improve understanding their relationship to robustness. | CS.arxiv | 2020-09-02 |
| 120 | Comprehensive Semantic Segmentation On High Resolution UAV Imagery For Natural Disaster Damage Assessment | MARYAM RAHNEMOONFAR et. al. | In this paper, we present a large-scale hurricane Michael dataset for visual perception in disaster scenarios, and analyze state-of-the-art deep neural network models for semantic segmentation. | CS.arxiv | 2020-09-02 |
| 121 | Spatial Transformer Point Convolution | YUAN FANG et. al. | In this paper, we propose a spatial transformer point convolution (STPC) method to achieve anisotropic convolution filtering on point clouds. | CS.arxiv | 2020-09-02 |
| 122 | Multi-domain Semantic Segmentation With Pyramidal Fusion | MARIN ORŠIĆ et. al. | We present our submission to the semantic segmentation contest of the Robust Vision Challenge held at ECCV 2020. | CS.arxiv | 2020-09-02 |
| 123 | Semantically Adaptive Image-to-image Translation For Domain Adaptation Of Semantic Segmentation | LUIGI MUSTO et. al. | In this paper, we address the problem of domain adaptation for semantic segmentation of street scenes. | CS.arxiv | 2020-09-02 |
| 124 | LSMVOS: Long-Short-Term Similarity Matching For Video Object | ZHANG XUERUI et. al. | Conclusion: The short-term matching module proposed in this paper is more conducive to extracting the information of the previous frame than only the mask. | CS.arxiv | 2020-09-01 |
| 125 | 3D-DEEP: 3-Dimensional Deep-learning Based On Elevation Patterns Forroad Scene Interpretation | A. HERNÁNDEZ et. al. | The developed models were trained and validated over Cityscapes dataset using just fine annotation examples with 19 different training classes, and over KITTI road dataset. | CS.arxiv | 2020-09-01 |
| 126 | Deep Ice Layer Tracking And Thickness Estimation Using Fully Convolutional Networks | MARYAM RAHNEMOONFAR et. al. | In this paper, we introduce a novel way of estimating the thickness of each internal ice layer using Snow Radar images and Fully Convolutional Networks. | CS.arxiv | 2020-08-31 |
| 127 | A Federated Approach For Fine-Grained Classification Of Fashion Apparel | TEJASWINI MALLAVARAPU et. al. | In contrast to most prior efforts, this paper aims to enable an in-depth classification of fashion item attributes within the same category. | CS.arxiv | 2020-08-27 |
| 128 | Attribute-guided Image Generation From Layout | KE MA et. al. | To address this limitation, we propose a new image generation method that enables instance-level attribute control. | CS.arxiv | 2020-08-27 |
| 129 | Instance Adaptive Self-Training For Unsupervised Domain Adaptation | KE MEI et. al. | In this paper, we propose an instance adaptive self-training framework for UDA on the task of semantic segmentation. | CS.arxiv | 2020-08-27 |
| 130 | Random Style Transfer Based Domain Generalization Networks Integrating Shape And Spatial Information | LEI LI et. al. | In this work, we present a random style transfer network to tackle the domain generalization problem for multi-vendor and center cardiac image segmentation. | CS.arxiv | 2020-08-27 |
| 131 | Visual Concept Reasoning Networks | TAESUP KIM et. al. | In this work, we propose to exploit this strategy and combine it with our Visual Concept Reasoning Networks (VCRNet) to enable reasoning between high-level visual concepts. | CS.arxiv | 2020-08-26 |
| 132 | Applying Surface Normal Information In Drivable Area And Road Anomaly Detection For Ground Mobile Robots | HENGLI WANG et. al. | Therefore, we develop a novel module named the Normal Inference Module (NIM), which can generate surface normal information from dense depth images with high accuracy and efficiency. | CS.arxiv | 2020-08-26 |
| 133 | Making A Case For 3D Convolutions For Object Segmentation In Videos | SABARINATH MAHADEVAN et. al. | In this work, we show that 3D CNNs can be effectively applied to dense video prediction tasks such as salient object segmentation. | CS.arxiv | 2020-08-26 |
| 134 | SNE-RoadSeg: Incorporating Surface Normal Information Into Semantic Segmentation For Accurate Freespace Detection | RUI FAN et. al. | The recent efforts made in data-fusion convolutional neural networks (CNNs) have significantly improved semantic driving scene segmentation. | CS.arxiv | 2020-08-25 |
| 135 | Mask-guided Sample Selection For Semi-Supervised Instance Segmentation | MIRIAM BELLVER et. al. | In this work, we propose a sample selection approach to decide which samples to annotate for semi-supervised instance segmentation. | CS.arxiv | 2020-08-25 |
| 136 | Deep Neural Network For 3D Surface Segmentation Based On Contour Tree Hierarchy | WENCHONG HE et. al. | In contrast, we propose to represent surface topological structure by a contour tree skeleton, which is a polytree capturing the evolution of surface contours at different elevation levels. | CS.arxiv | 2020-08-25 |
| 137 | CSCL: Critical Semantic-Consistent Learning For Unsupervised Domain Adaptation | JIAHUA DONG et. al. | To address above challenges, we develop a new Critical Semantic-Consistent Learning (CSCL) model, which mitigates the discrepancy of both domain-wise and category-wise distributions. | CS.arxiv | 2020-08-24 |
| 138 | Probabilistic Deep Learning For Instance Segmentation | JOSEF LORENZ RUMBERGER et. al. | We seek to close this gap by proposing a generic method to obtain model-inherent uncertainty estimates within proposal-free instance segmentation models. | CS.arxiv | 2020-08-24 |
| 139 | Semantic Labeling Of Large-Area Geographic Regions Using Multi-View And Multi-Date Satellite Images, And Noisy OSM Training Labels | BHARATH COMANDUR et. al. | We present a novel multi-view training framework and CNN architecture for combining information from multiple overlapping satellite images and noisy training labels derived from OpenStreetMap (OSM) for semantic labeling of buildings and roads across large geographic regions (100 km$^2$). | CS.arxiv | 2020-08-24 |
| 140 | LULC Segmentation Of RGB Satellite Image Using FCN-8 | ABU BAKAR SIDDIK NAYEM et. al. | Specically, we propose a non-overlapping grid-based approach to train a Fully Convo-lutional Network (FCN-8) with vgg-16 weights to segment satellite im-ages into four (forest, built-up, farmland and water) classes. | CS.arxiv | 2020-08-24 |
| 141 | EfficientFCN: Holistically-guided Decoding For Semantic Segmentation | JIANBO LIU et. al. | In this paper, we propose the EfficientFCN, whose backbone is a common ImageNet pre-trained network without any dilated convolution. | CS.arxiv | 2020-08-24 |
| 142 | TORNADO-Net: MulTiview TOtal VaRiatioN SemAntic Segmentation With Diamond InceptiOn Module | MARTIN GERDZHEV et. al. | In this paper, we introduce TORNADO-Net – a neural network for 3D LiDAR point cloud semantic segmentation. | CS.arxiv | 2020-08-24 |
| 143 | Seesaw Loss For Long-Tailed Instance Segmentation | JIAQI WANG et. al. | This report presents the approach used in the submission of the LVIS Challenge 2020 of team MMDet. | CS.arxiv | 2020-08-23 |
| 144 | M2caiSeg: Semantic Segmentation Of Laparoscopic Images Using Convolutional Neural Networks | SALMAN MAQBOOL et. al. | We propose a new dataset and a deep learning method for pixel level identification of various organs and instruments in a endoscopic surgical scene. | CS.arxiv | 2020-08-23 |
| 145 | Robust Vision Challenge 2020 — 1st Place Report For Panoptic Segmentation | ROHIT MOHAN et. al. | In this technical report, we present key details of our winning panoptic segmentation architecture EffPS_b1bs4_RVC. | CS.arxiv | 2020-08-23 |
| 146 | One Weight Bitwidth To Rule Them All | TING-WU CHIN et. al. | In this work, we take the first step to understand if some weight bitwidth is better than others by aligning all to the same model size using a width-multiplier. | CS.arxiv | 2020-08-22 |
| 147 | Symbolic Semantic Segmentation And Interpretation Of COVID-19 Lung Infections In Chest CT Volumes Based On Emergent Languages | ARITRA CHOWDHURY et. al. | Inspired by human communication of complex ideas through language, we propose a symbolic framework based on emergent languages for the segmentation of COVID-19 infections in CT scans of lungs. | CS.arxiv | 2020-08-22 |
| 148 | ScribbleBox: Interactive Annotation Framework For Video Object Segmentation | BOWEN CHEN et. al. | In this paper, we introduce ScribbleBox, a novel interactive framework for annotating object instances with masks in videos. | CS.arxiv | 2020-08-21 |
| 149 | Learning To Predict Context-adaptive Convolution For Semantic Segmentation | JIANBO LIU et. al. | In this paper, we propose a Context-adaptive Convolution Network (CaC-Net) to predict a spatially-varying feature weighting vector for each spatial location of the semantic feature maps. | CS.eccv | 2020-08-21 |
| 150 | Funnel Activation For Visual Recognition | NINGNING MA et. al. | We present a conceptually simple but effective funnel activation for image recognition tasks, called Funnel activation (FReLU), that extends ReLU and PReLU to a 2D activation by adding a negligible overhead of spatial condition. | CS.eccv | 2020-08-21 |
| 151 | Segmenting Transparent Objects In The Wild | ENZE XIE et. al. | To address this important problem, this work proposes a large-scale dataset for transparent object segmentation, named Trans10K, consisting of 10,428 images of real scenarios with carefully manual annotations, which are 10 times larger than the existing datasets. | CS.eccv | 2020-08-21 |
| 152 | Spatial Attention Pyramid Network For Unsupervised Domain Adaptation | CONGCONG LI et. al. | To that end, in this paper, we design a new spatial attention pyramid network for unsupervised domain adaptation. | CS.eccv | 2020-08-21 |
| 153 | ForkGAN: Seeing Into The Rainy Night | ZIQIANG ZHENG et. al. | We present a ForkGAN for task-agnostic image translation that can boost multiple vision tasks in adverse weather conditions. | CS.eccv | 2020-08-21 |
| 154 | Efficient Semantic Video Segmentation With Per-frame Inference | YIFAN LIU et. al. | In contrast, here we explicitly consider the temporal consistency among frames as extra constraints during training and process each frame independently in the inference phase. | CS.eccv | 2020-08-21 |
| 155 | Memory Selection Network For Video Propagation | RUIZHENG WU et. al. | To tackle this challenge, we propose a memory selection network, which learns to select suitable guidance from all previous frames for effective and robust propagation. | CS.eccv | 2020-08-21 |
| 156 | Negative Pseudo Labeling Using Class Proportion For Semantic Segmentation In Pathology | HIROKI TOKUNAGA et. al. | In this paper, we propose a subtype segmentation method that uses such proportional labels as weakly supervised labels. | CS.eccv | 2020-08-21 |
| 157 | Post-Training Piecewise Linear Quantization For Deep Neural Networks | JUN FANG et. al. | In this paper, we propose a PieceWise Linear Quantization (PWLQ) scheme to enable accurate approximation for tensor values that have bell-shaped distributions with long tails. | CS.eccv | 2020-08-21 |
| 158 | Learning Discriminative Feature With CRF For Unsupervised Video Object Segmentation | MINGMIN ZHEN et. al. | In this paper, we introduce a novel network, called discriminative feature network (DFNet), to address the unsupervised video object segmentation task. | CS.eccv | 2020-08-21 |
| 159 | Virtual Multi-view Fusion For 3D Semantic Segmentation | ABHIJIT KUNDU et. al. | In this paper we revisit the classic multiview representation of 3D meshes and study several techniques that make them effective for 3D semantic segmentation of meshes. | CS.eccv | 2020-08-21 |
| 160 | Self-Supervised CycleGAN For Object-Preserving Image-to-Image Domain Adaptation | XINPENG XIE et. al. | In this paper, we propose a novel GAN (namely OP-GAN) to address the problem, which involves a self-supervised module to enforce the image content consistency during image-to-image translations without any extra annotations. | CS.eccv | 2020-08-21 |
| 161 | Efficient Scale-Permuted Backbone With Learned Resource Distribution | XIANZHI DU et. al. | In this work, we propose a simple technique to combine efficient operations and compound scaling with a previously learned scale-permuted architecture. | CS.eccv | 2020-08-21 |
| 162 | Bi-directional Cross-Modality Feature Propagation With Separation-and-Aggregation Gate For RGB-D Semantic Segmentation | XIAOKANG CHEN et. al. | In this paper, we propose a unified and efficient Cross-modality Guided Encoder to not only effectively recalibrate RGB feature responses, but also to distill accurate depth information via multiple stages and aggregate the two recalibrated representations alternatively. | CS.eccv | 2020-08-21 |
| 163 | Learning What To Learn For Video Object Segmentation | GOUTAM BHAT et. al. | We address this by introducing an end-to-end trainable VOS architecture that integrates a differentiable few-shot learner. | CS.eccv | 2020-08-21 |
| 164 | Delving Deeper Into Anti-aliasing In ConvNets | XUEYAN ZOU et. al. | To tackle this, we propose an adaptive content-aware low-pass filtering layer, which predicts separate filter weights for each spatial location and channel group of the input feature maps. | CS.arxiv | 2020-08-21 |
| 165 | URVOS: Unified Referring Video Object Segmentation Network With A Large-Scale Benchmark | SEONGUK SEO et. al. | We propose a unified referring video object segmentation network (URVOS). | CS.eccv | 2020-08-21 |
| 166 | Sketching Image Gist: Human-Mimetic Hierarchical Scene Graph Generation | WENBIN WANG et. al. | Therefore, we argue that a desirable scene graph should be also hierarchically constructed, and introduce a new scheme for modeling scene graph. | CS.eccv | 2020-08-21 |
| 167 | Dynamic And Static Context-aware LSTM For Multi-agent Motion Prediction | CHAOFAN TAO et. al. | However, unlike previous work that isolated the spatial interaction, temporal coherence, and scene layout, this paper designs a new mechanism, \ie, Dynamic and Static Context-aware Motion Predictor (DSCMP), to integrates these rich information into the long-short-term-memory (LSTM). | CS.eccv | 2020-08-21 |
| 168 | Deep FusionNet For Point Cloud Semantic Segmentation | FEIHU ZHANG JIN FANG BENJAMIN WAH PHILIP TORR | To address these issues, we propose a deep fusion network architecture (FusionNet) with a unique voxel-based mini-PointNet point cloud representation and a new feature aggregation module (fusion module) for large-scale 3D semantic segmentation. | CS.eccv | 2020-08-21 |
| 169 | Fast Video Object Segmentation Using The Global Context Module | YU LI et. al. | We developed a real-time, high-quality semi-supervised video object segmentation algorithm. | CS.eccv | 2020-08-21 |
| 170 | Classes Matter: A Fine-grained Adversarial Approach To Cross-domain Semantic Segmentation | HAORAN WANG et. al. | To fully exploit the supervision in the source domain, we propose a fine-grained adversarial learning strategy for class-level feature alignment while preserving the internal structure of semantics across domains. | CS.eccv | 2020-08-21 |
| 171 | Malleable 2.5D Convolution: Learning Receptive Fields Along The Depth-axis For RGB-D Scene Parsing | YAJIE XING et. al. | In this paper, we propose a novel operator called malleable 2.5D convolution to learn the receptive field along the depth-axis. | CS.eccv | 2020-08-21 |
| 172 | JSENet: Joint Semantic Segmentation And Edge Detection Network For 3D Point Clouds | ZEYU HU et. al. | In this paper, we tackle the 3D semantic edge detection task for the first time and present a new two-stream fully-convolutional network that jointly performs the two tasks. | CS.eccv | 2020-08-21 |
| 173 | Collaborative Video Object Segmentation By Foreground-Background Integration | ZONGXIN YANG et. al. | This paper investigates the principles of embedding learning to tackle the challenging semi-supervised video object segmentation. | CS.eccv | 2020-08-21 |
| 174 | Self-Prediction For Joint Instance And Semantic Segmentation Of Point Clouds | JINXIAN LIU et. al. | We develop a novel learning scheme named Self-Prediction for 3D instance and semantic segmentation of point clouds. | CS.eccv | 2020-08-21 |
| 175 | Increasing The Robustness Of Semantic Segmentation Models With Painting-by-Numbers | CHRISTOPH KAMANN et. al. | We present a new training schema that increases this shape bias. | CS.eccv | 2020-08-21 |
| 176 | SOLO: Segmenting Objects By Locations | XINLONG WANG et. al. | We present a new, embarrassingly simple approach to instance segmentation in images. | CS.eccv | 2020-08-21 |
| 177 | Continuous Adaptation For Interactive Object Segmentation By Learning From Corrections | THEODORA KONTOGIANNI et. al. | Instead, we recognize that user corrections can serve as sparse training examples and we propose a method that capitalizes on that idea to update the model parameters on-the-fly to the data at hand. | CS.eccv | 2020-08-21 |
| 178 | End-to-End Trainable Deep Active Contour Models For Automated Image Segmentation: Delineating Buildings In Aerial Imagery | ALI HATAMIZADEH et. al. | As a solution, we present Trainable Deep Active Contours (TDACs), an automatic image segmentation framework that intimately unites Convolutional Neural Networks (CNNs) and Active Contour Models (ACMs). | CS.eccv | 2020-08-21 |
| 179 | PhraseClick: Toward Achieving Flexible Interactive Segmentation By Phrase And Click | HENGHUI DING et. al. | We propose to employ phrase expressions as another interaction input to infer the attributes of target object. | CS.eccv | 2020-08-21 |
| 180 | Unsupervised Video Object Segmentation With Joint Hotspot Tracking | LU ZHANG et. al. | Specifically, we propose a Weighted Correlation Siamese Network (WCS-Net) which employs a Weighted Correlation Block (WCB) for encoding the pixel-wise correspondence between a template frame and the search frame. | CS.eccv | 2020-08-21 |
| 181 | Attend And Segment: Attention Guided Active Semantic Segmentation | SOROUSH SEIFI et. al. | In this paper we propose a method to gradually segment a scene given a sequence of partial observations. | CS.eccv | 2020-08-21 |
| 182 | Domain Adaptive Semantic Segmentation Using Weak Labels | SUJOY PAUL et. al. | We propose a novel framework for domain adaptation in semantic segmentation with image-level weak labels in the target domain. In experiments, we show considerable improvements with respect to the existing state-of-the-arts in UDA and present a new benchmark in the WDA setting. | CS.eccv | 2020-08-21 |
| 183 | ScribbleBox: Interactive Annotation Framework For Video Object Segmentation | BOWEN CHEN et. al. | We introduce ScribbleBox, an interactive framework for annotating object instances with masks in videos with a significant boost in efficiency. | CS.eccv | 2020-08-21 |
| 184 | Employing Multi-Estimations For Weakly-Supervised Semantic Segmentation | JUNSONG FAN et. al. | Instead of struggling to refine a single seed, we propose a novel approach to alleviate the inaccurate seed problem by leveraging the segmentation model’s robustness to learn from multiple seeds. | CS.eccv | 2020-08-21 |
| 185 | Box2Seg: Attention Weighted Loss And Discriminative Feature Learning For Weakly Supervised Segmentation | VIVEKA KULHARIA et. al. | We propose a weakly supervised approach to semantic segmentation using bounding box annotations. | CS.eccv | 2020-08-21 |
| 186 | Naive-Student: Leveraging Semi-Supervised Learning In Video Sequences For Urban Scene Segmentation | LIANG-CHIEH CHEN et. al. | In this work, we ask if we may leverage semi-supervised learning in unlabeled video sequences and extra images to improve the performance on urban scene segmentation, simultaneously tackling semantic, instance, and panoptic segmentation. | CS.eccv | 2020-08-21 |
| 187 | Learning Object Depth From Camera Motion And Video Object Segmentation | BRENT A. GRIFFIN et. al. | To leverage this progress in 3D applications, this paper addresses the problem of learning to estimate the depth of segmented objects given some measurement of camera motion (e.g., from robot kinematics or vehicle odometry). | CS.eccv | 2020-08-21 |
| 188 | Polynomial Regression Network For Variable-Number Lane Detection | BINGKE WANG et. al. | In this work, we propose to use polynomial curves to represent traffic lanes and then propose a novel polynomial regression network (PRNet) to directly predict them, where semantic segmentation is not involved. | CS.eccv | 2020-08-21 |
| 189 | Learning From Scale-Invariant Examples For Domain Adaptation In Semantic Segmentation | M.NASEER SUBHANI et. al. | In this paper, we propose a novel approach of exploiting scale-invariance property of the semantic segmentation model for self-supervised domain adaptation. | CS.eccv | 2020-08-21 |
| 190 | GINet: Graph Interaction Network For Scene Parsing | TIANYI WU et. al. | In this work, we explore how to incorperate the linguistic knowledge to promote context reasoning over image regions by proposing a Graph Interaction unit (GI unit) and a Semantic Context Loss (SC-loss). | CS.eccv | 2020-08-21 |
| 191 | Mining Self-similarity: Label Super-resolution With Epitomic Representations | NIKOLAY MALKIN et. al. | We derive a new training algorithm for epitomes which allows, for the first time, learning from very large data sets and derive a label super-resolution algorithm as a statistical inference algorithm over epitomic representations. | CS.eccv | 2020-08-21 |
| 192 | Contextual Diversity For Active Learning | SHARAT AGARWAL et. al. | Since the context is difficult to evaluate in the absence of ground-truth labels, we introduce the notion of contextual diversity that captures the confusion associated with spatially co-occurring classes. | CS.eccv | 2020-08-21 |
| 193 | Intra-class Feature Variation Distillation For Semantic Segmentation | YUKANG WANG et. al. | In this paper, different from previous methods performing knowledge distillation for densely pairwise relations, we propose a novel intra-class feature variation distillation (IFVD) to transfer the intra-class feature variation (IFV) of the cumbersome model (teacher) to the compact model (student). | CS.eccv | 2020-08-21 |
| 194 | Tensor Low-Rank Reconstruction For Semantic Segmentation | WANLI CHEN et. al. | In this paper, we propose a new approach to model the 3D context representations,which not only avoids the space compression, but also tackles the high-rank difficulty. | CS.eccv | 2020-08-21 |
| 195 | Video Object Segmentation With Episodic Graph Memory Networks | XIANKAI LU et. al. | In this work, a graph memory network is developed to address the novel idea of “learning to update the segmentation model”. | CS.eccv | 2020-08-21 |
| 196 | Interactive Video Object Segmentation Using Global And Local Transfer Modules | YUK HEO et. al. | An interactive video object segmentation algorithm, which takes scribble annotations on query objects as input, is proposed in this paper. | CS.eccv | 2020-08-21 |
| 197 | Representative Graph Neural Network | CHANGQIAN YU et. al. | In this paper, we present a Representative Graph (RepGraph) layer to dynamically sample a few representative features, which dramatically reduces redundancy. | CS.eccv | 2020-08-21 |
| 198 | Regularized Loss For Weakly Supervised Single Class Semantic Segmentation | OLGA VEKSLER | We propose a new weakly supervised method for training CNNs to segment an object of a single class of interest. | CS.eccv | 2020-08-21 |
| 199 | Indirect Local Attacks For Context-aware Semantic Segmentation Networks | KRISHNA KANTH NAKKA et. al. | To this end, we introduce an indirect attack strategy, namely adaptive local attacks, aiming to find the best image location to perturb, while preserving the labels at this location and producing a realistic-looking segmentation map. | CS.eccv | 2020-08-21 |
| 200 | Semi-supervised Semantic Segmentation Via Strong-weak Dual-branch Network | WENFENG LUO et. al. | To fully explore the potential of the weak labels, we propose to impose separate treatments of strong and weak annotations via a strong-weakdual-branch network, which discriminates the massive inaccurate weak supervisions from those strong ones. | CS.eccv | 2020-08-21 |
| 201 | Self-similarity Student For Partial Label Histopathology Image Segmentation | HSIEN-TZU CHENG et. al. | To learn from these patches, we propose Self-similarity Student, combining teacher-student model paradigm with similarity learning. | CS.eccv | 2020-08-21 |
| 202 | Semantic Segmentation And Data Fusion Of Microsoft Bing 3D Cities And Small UAV-based Photogrammetric Data | MEIDA CHEN et. al. | In this study, the authors first investigated the strengths and limitations of the existing framework when applied to the Bing data. | CS.arxiv | 2020-08-21 |
| 203 | SideInfNet: A Deep Neural Network For Semi-Automatic Semantic Segmentation With Side Information | JING YU KOH et. al. | Inspired by the practicality and applicability of the semi-automatic approach, this paper proposes a novel deep neural network architecture, namely SideInfNet that effectively integrates features learnt from images with side information extracted from user annotations. | CS.eccv | 2020-08-21 |
| 204 | GMNet: Graph Matching Network For Large Scale Part Semantic Segmentation In The Wild | UMBERTO MICHIELI et. al. | In this work, we propose a novel framework combining higher object-level context conditioning and part-level spatial relationships to address the task. | CS.eccv | 2020-08-21 |
| 205 | Regression Of Instance Boundary By Aggregated CNN And GCN | YANDA MENG et. al. | This paper proposes a straightforward, intuitive deep learning approach for (biomedical) image segmentation tasks. | CS.eccv | 2020-08-21 |
| 206 | Splitting Vs. Merging: Mining Object Regions With Discrepancy And Intersection Loss For Weakly Supervised Semantic Segmentation | TIANYI ZHANG et. al. | In this paper we focus on the task of weakly-supervised semantic segmentation supervised with image-level labels. | CS.eccv | 2020-08-21 |
| 207 | Beyond Monocular Deraining: Stereo Image Deraining Via Semantic Understanding | KAIHAO ZHANG et. al. | In this paper, we present a Paired Rain Removal Network (PRRNet), which exploits both stereo images and semantic information. | CS.eccv | 2020-08-21 |
| 208 | Synthesize Then Compare: Detecting Failures And Anomalies For Semantic Segmentation | YINGDA XIA et. al. | In this paper, we systematically study failure and anomaly detection for semantic segmentation and propose a unified framework, consisting of two modules, to address these two related problems. | CS.eccv | 2020-08-21 |
| 209 | Object-Contextual Representations For Semantic Segmentation | YUHUI YUAN et. al. | In this paper, we address the semantic segmentation problem with a focus on the context aggregation strategy. | CS.eccv | 2020-08-21 |
| 210 | Content-Consistent Matching For Domain Adaptive Semantic Segmentation | GUANGRUI LI et. al. | This paper considers the adaptation of semantic segmentation from the synthetic source domain to the real target domain. | CS.eccv | 2020-08-21 |
| 211 | Autoregressive Unsupervised Image Segmentation | YASSINE OUALI et. al. | In this work, we propose a new unsupervised image segmentation approach based on mutual information maximization between different constructed views of the inputs. | CS.eccv | 2020-08-21 |
| 212 | GeoLayout: Geometry Driven Room Layout Estimation Based On Depth Maps Of Planes | WEIDONG ZHANG et. al. | In this work, we propose to incorporate geometric reasoning to deep learning for layout estimation. Moreover, we present a new dataset with pixel-level depth annotation of dominant planes. | CS.eccv | 2020-08-21 |
| 213 | Guidance And Evaluation: Semantic-Aware Image Inpainting For Mixed Scenes | LIANG LIAO et. al. | In this paper, we propose a Semantic Guidance and Evaluation Network (SGE-Net) to iteratively update the structural priors and the inpainted image in an interplay framework of semantics extraction and image inpainting. | CS.eccv | 2020-08-21 |
| 214 | Guided Collaborative Training For Pixel-wise Semi-Supervised Learning | ZHANGHAN KE et. al. | In this paper, we present a new SSL framework, named Guided Collaborative Training (GCT), for pixel-wise tasks, with two main technical contributions. | CS.eccv | 2020-08-21 |
| 215 | Duality Diagram Similarity: A Generic Framework For Initialization Selection In Task Transfer Learning | KSHITIJ DWIVEDI et. al. | In this paper, we tackle an open research question in transfer learning, which is selecting a model initialization to achieve high performance on a new task, given several pre-trained models. | CS.eccv | 2020-08-21 |
| 216 | Mining Cross-Image Semantics For Weakly Supervised Semantic Segmentation | GUOLEI SUN et. al. | This paper studies the problem of learning semantic segmentation from image-level supervision only. | CS.eccv | 2020-08-21 |
| 217 | Kernelized Memory Network For Video Object Segmentation | HONGJE SEONG et. al. | To solve the mismatch between STM and VOS, we propose a kernelized memory network (KMN). | CS.eccv | 2020-08-21 |
| 218 | Improving Semantic Segmentation Via Decoupled Body And Edge Supervision | XIANGTAI LI et. al. | In this paper, a new paradigm for semantic segmentation is proposed. | CS.eccv | 2020-08-21 |
| 219 | Lifespan Age Transformation Synthesis | ROY OR-EL et. al. | We propose a new multi domain image-to-image generative adversarial network architecture, whose learned latent space accurately models the continuous aging process in both directions. | CS.eccv | 2020-08-21 |
| 220 | Efficient Outdoor 3D Point Cloud Semantic Segmentation For Critical Road Objects And Distributed Contexts | CHI-CHONG WONG et. al. | In this work, we propose a novel neural network model called Attention-based Dynamic Convolution Network with Self-Attention Global Contexts(ADConvnet-SAGC), which i) applies attention mechanism to adaptively focus on the most related neighboring points for learning the point features of 3D objects, especially for small objects with diverse shapes ii) applies self-attention module for efficiently capturing long-range distributed contexts from the input iii) a more reasonable and compact architecture for efficient inference. | CS.eccv | 2020-08-21 |
| 221 | Self-Supervised Monocular Depth Estimation: Solving The Dynamic Object Problem By Semantic Guidance | MARVIN KLINGNER et. al. | In this work we present a new self-supervised semantically-guided depth estimation (SGDepth) method to deal with moving dynamic-class (DC) objects, such as moving cars and pedestrians, which violate the static-world assumptions typically made during training of such models. | CS.eccv | 2020-08-21 |
| 222 | Unsupervised Domain Adaptation For Semantic Segmentation Of NIR Images Through Generative Latent Search | PRASHANT PANDEY et. al. | We propose a method for target-independent segmentation where the ‘nearest-clone’ of a target image in the source domain is searched and used as a proxy in the segmentation network trained only on the source domain. | CS.eccv | 2020-08-21 |
| 223 | Few-Shot Semantic Segmentation With Democratic Attention Networks | HAOCHEN WANG et. al. | In this paper, we propose the Democratic Attention Network (DAN) for few-shot semantic segmentation. | CS.eccv | 2020-08-21 |
| 224 | Semantic Flow For Fast And Accurate Scene Parsing | XIANGTAI LI et. al. | In this paper, we focus on designing effective method for fast and accurate scene parsing. | CS.eccv | 2020-08-21 |
| 225 | Class-wise Dynamic Graph Convolution For Semantic Segmentation | HANZHE HU et. al. | In order to avoid potential misleading contextual information aggregation in previous work, we propose a class-wise dynamic graph convolution(CDGC) module to adaptively propagate information. | CS.eccv | 2020-08-21 |
| 226 | Weakly Supervised Semantic Segmentation With Boundary Exploration | LIYI CHEN et. al. | To obtain semantic segmentation under weak supervision, this paper presents a simple yet effective approach based on the idea of explicitly exploring object boundaries from training images to keep coincidence of segmentation and boundaries. | CS.eccv | 2020-08-21 |
| 227 | Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs By Implicitly Unprojecting To 3D | JONAH PHILION et. al. | We propose a new end-to-end architecture that directly extracts a bird’s-eye-view representation of a scene given image data from an arbitrary number of cameras. | CS.eccv | 2020-08-21 |
| 228 | Contextual-Relation Consistent Domain Adaptation For Semantic Segmentation | JIAXING HUANG et. al. | This paper presents an innovative local contextual-relation consistent domain adaptation (CrCDA) technique that aims to achieve local-level consistencies during the global-level alignment. | CS.eccv | 2020-08-21 |
| 229 | Multi-scale Interaction For Real-time LiDAR Data Segmentation On An Embedded Platform | SHIJIE LI et. al. | In this paper, we therefore propose a projection-based method, called Multi-scale Interaction Network (MINet), which is very efficient and accurate. | CS.arxiv | 2020-08-20 |
| 230 | ISSAFE: Improving Semantic Segmentation In Accidents By Fusing Event-based Data | JIAMING ZHANG et. al. | To tackle this issue, we present a rarely addressed task regarding semantic segmentation in accident scenarios, along with an associated large-scale dataset DADA-seg. | CS.arxiv | 2020-08-20 |
| 231 | Beyond Fixed Grid: Learning Geometric Image Representation With A Deformable Grid | JUN GAO et. al. | We introduce \emph{Deformable Grid} DefGrid, a learnable neural network module that predicts location offsets of vertices of a 2-dimensional triangular grid, such that the edges of the deformed grid align with image boundaries. | CS.arxiv | 2020-08-20 |
| 232 | SegCodeNet: Color-Coded Segmentation Masks For Activity Detection From Wearable Cameras | ASIF SHAHRIYAR SUSHMIT et. al. | In this work, we developed a two-stream network, the \emph{SegCodeNet}, that uses a network branch containing video-streams with color-coded semantic segmentation masks of relevant objects in addition to the original RGB video-stream. | CS.arxiv | 2020-08-19 |
| 233 | PC-U Net: Learning To Jointly Reconstruct And Segment The Cardiac Walls In 3D From CT Data | MENG YE et. al. | In this paper, we propose a PC-U net that jointly reconstructs the point cloud of the LV MYO wall directly from volumes of 2D CT slices and generates its segmentation masks from the predicted 3D point cloud. | CS.arxiv | 2020-08-18 |
| 234 | Geodesic Paths For Image Segmentation With Implicit Region-based Homogeneity Enhancement | DA CHEN et. al. | In this paper, we introduce a flexible interactive image segmentation model based on the minimal geodesic framework in conjunction with region-based homogeneity enhancement. | CS.arxiv | 2020-08-16 |
| 235 | We Learn Better Road Pothole Detection: From Attention Aggregation To Adversarial Domain Adaptation | RUI FAN et. al. | To boost the performance, we propose a novel attention aggregation (AA) framework, which takes the advantages of different types of attention modules. | CS.arxiv | 2020-08-16 |
| 236 | InstanceMotSeg: Real-time Instance Motion Segmentation For Autonomous Driving | ESLAM MOHAMED et. al. | In this paper, we proposed a motion-based instance segmentation task and created a new annotated dataset based on KITTI, which will be released publicly. | CS.arxiv | 2020-08-16 |
| 237 | Time-Supervised Primary Object Segmentation | YANCHAO YANG et. al. | We describe an unsupervised method to detect and segment portions of live scenes that, at some point in time, are seen moving as a coherent whole, which we refer to as primary objects. | CS.arxiv | 2020-08-16 |
| 238 | Attack On Multi-Node Attention For Object Detection | SIZHE CHEN et. al. | This paper focuses on high-transferable adversarial attacks on detection networks, which are crucial for life-concerning systems such as autonomous driving and security surveillance. | CS.arxiv | 2020-08-15 |
| 239 | Curriculum Learning For Recurrent Video Object Segmentation | MARIA GONZALEZ-I-CALABUIG et. al. | This work explores different schedule sampling and frame skipping variations to significantly improve the performance of a recurrent architecture. | CS.arxiv | 2020-08-15 |
| 240 | Feedback Attention For Cell Image Segmentation | HIROKI TSUDA et. al. | In this paper, we address cell image segmentation task by Feedback Attention mechanism like feedback processing. | CS.arxiv | 2020-08-14 |
| 241 | Optimized Deep Encoder-Decoder Methods For Crack Segmentation | JACOB KÖNIG et. al. | In this work we propose optimized deep encoder-decoder methods consisting of a combination of techniques which yield an increase in crack segmentation performance. | CS.arxiv | 2020-08-14 |
| 242 | Towards Visually Explaining Similarity Models | MENG ZHENG et. al. | In this work, we bridge this crucial gap, presenting the first method to generate gradient-based visual explanations for image similarity predictors. | CS.arxiv | 2020-08-13 |
| 243 | Sparse Coding Driven Deep Decision Tree Ensembles For Nuclear Segmentation In Digital Pathology Images | JIE SONG et. al. | In this paper, we propose an easily trained yet powerful representation learning approach with performance highly competitive to deep neural networks in a digital pathology image segmentation task. | CS.arxiv | 2020-08-12 |
| 244 | Guided Collaborative Training For Pixel-wise Semi-Supervised Learning | ZHANGHAN KE et. al. | In this paper, we present a new SSL framework, named Guided Collaborative Training (GCT), for pixel-wise tasks, with two main technical contributions. | CS.arxiv | 2020-08-12 |
| 245 | Pixel-level Corrosion Detection On Metal Constructions By Fusion Of Deep Learning Semantic And Contour Segmentation | IASON KATSAMENIS et. al. | In this paper, we apply three semantic segmentation-oriented deep learning models (FCN, U-Net and Mask R-CNN) for corrosion detection, which perform better in terms of accuracy and time and require a smaller number of annotated samples compared to other deep models, e.g. CNN. | CS.arxiv | 2020-08-12 |
| 246 | Local Temperature Scaling For Probability Calibration | ZHIPENG DING et. al. | Thus, we propose a learning-based calibration method that focuses on multi-label semantic segmentation. | CS.arxiv | 2020-08-12 |
| 247 | Feature Binding With Category-Dependant MixUp For Semantic Segmentation And Adversarial Robustness | MD AMIRUL ISLAM et. al. | In this paper, we present a strategy for training convolutional neural networks to effectively resolve interference arising from competing hypotheses relating to inter-categorical information throughout the network. | CS.arxiv | 2020-08-12 |
| 248 | Reinforced Wasserstein Training For Severity-Aware Semantic Segmentation In Autonomous Driving | XIAOFENG LIU et. al. | Targeting for this difficulty, we develop a Wasserstein training framework to explore the inter-class correlation by defining its ground metric as misclassification severity. | CS.arxiv | 2020-08-11 |
| 249 | Image Segmentation Via Cellular Automata | MARK SANDLER et. al. | In this paper, we propose a new approach for building cellular automata to solve real-world segmentation problems. | CS.arxiv | 2020-08-11 |
| 250 | Dynamic Object Removal And Spatio-Temporal RGB-D Inpainting Via Geometry-Aware Adversarial Learning | BORNA BEŠIĆ et. al. | In this work, we address this problem by synthesizing plausible color, texture and geometry in regions occluded by dynamic objects. We introduce a large-scale hyperrealistic dataset with RGB-D images, semantic segmentation labels, camera poses as well as ground truth RGB-D information of occluded regions. | CS.arxiv | 2020-08-11 |
| 251 | Prototype Mixture Models For Few-shot Semantic Segmentation | BOYU YANG et. al. | In this paper, we propose prototype mixture models (PMMs), which correlate diverse image regions with multiple prototypes to enforce the prototype-based semantic representation. | CS.arxiv | 2020-08-10 |
| 252 | SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized With Semantic Segmentation For Autonomous Driving | VARUN RAVI KUMAR et. al. | In this paper, we introduce a novel multi-task learning strategy to improve self-supervised monocular distance estimation on fisheye and pinhole camera images. | CS.arxiv | 2020-08-10 |
| 253 | Projected-point-based Segmentation: A New Paradigm For LiDAR Point Cloud Segmentation | SHIJIE LI et. al. | To address such a domain gap, we propose a new paradigm, namely projected-point-based methods, to transform point-based methods to a suitable form for LiDAR point cloud segmentation by utilizing the characteristics of LiDAR point clouds. | CS.arxiv | 2020-08-10 |
| 254 | Cylinder3D: An Effective 3D Framework For Driving-scene LiDAR Semantic Segmentation | HUI ZHOU et. al. | We evaluate the proposed model on a large-scale driving-scene dataset, i.e. SematicKITTI. | CS.arxiv | 2020-08-04 |
| 255 | Importance Of Self-Consistency In Active Learning For Semantic Segmentation | S. ALIREZA GOLESTANEH et. al. | We address the task of active learning in the context of semantic segmentation and show that self-consistency can be a powerful source of self-supervision to greatly improve the performance of a data-driven model with access to only a small amount of labeled data. | CS.arxiv | 2020-08-04 |
| 256 | Prior Guided Feature Enrichment Network For Few-Shot Segmentation | ZHUOTAO TIAN et. al. | To alleviate these issues, we propose the Prior Guided Feature Enrichment Network (PFENet). | CS.arxiv | 2020-08-04 |
| 257 | Frame-To-Frame Consistent Semantic Segmentation | MANUEL REBOL et. al. | In this work, we aim for temporally consistent semantic segmentation throughout frames in a video. | CS.arxiv | 2020-08-03 |
| 258 | Walking On Two Legs: Learning Image Segmentation With Noisy Labels | GUOHUA CHENG et. al. | In this paper, we propose a novel label refinement and sample reweighting method, and a novel generative adversarial network (GAN) is introduced to fuse these two models into an integrated framework. | CS.uai | 2020-08-03 |
| 259 | PhraseCut: Language-based Image Segmentation In The Wild | CHENYUN WU et. al. | We systematically handle the long-tail nature of these concepts and present a modular approach to combine category, attribute, and relationship cues that outperforms existing approaches. | CS.arxiv | 2020-08-03 |
| 260 | Central Object Segmentation By Deep Learning For Fruits And Other Roundish Objects | MOTOHISA FUKUDA et. al. | We present CROP (Central Roundish Object Painter), which identifies and paints the object at the center of an RGB image. | CS.arxiv | 2020-08-03 |
| 261 | Self-supervised Object Tracking With Cycle-consistent Siamese Networks | WEIHAO YUAN et. al. | In this work, we exploit an end-to-end Siamese network in a cycle-consistent self-supervised framework for object tracking. | CS.arxiv | 2020-08-03 |
| 262 | Weakly-Supervised Semantic Segmentation Via Sub-category Exploration | YU-TING CHANG et. al. | To enforce the network to pay attention to other parts of an object, we propose a simple yet effective approach that introduces a self-supervised task by exploiting the sub-category information. | CS.arxiv | 2020-08-03 |
| 263 | Mixup-CAM: Weakly-supervised Semantic Segmentation Via Uncertainty Regularization | YU-TING CHANG et. al. | To tackle this issue, we propose a principled and end-to-end train-able framework to allow the network to pay attention to other parts of the object, while producing a more complete and uniform response map. | CS.arxiv | 2020-08-03 |
| 264 | Tensor Low-Rank Reconstruction For Semantic Segmentation | WANLI CHEN et. al. | In this paper, we propose a new approach to model the 3D context representations, which not only avoids the space compression but also tackles the high-rank difficulty. | CS.arxiv | 2020-08-02 |
| 265 | State-of-The-Art Fuzzy Active Contour Models For Image Segmentation | AJOY MONDAL et. al. | In this article, our aim is to review the existing fuzzy active contour models from the theoretical point of view and also evaluate them experimentally on a large set of images under the various conditions. | CS.arxiv | 2020-08-01 |
| 266 | Meta-DRN: Meta-Learning For 1-Shot Image Segmentation | ATMADEEP BANERJEE | In this paper, we propose a novel lightweight CNN architecture for 1-shot image segmentation. | CS.arxiv | 2020-08-01 |
| 267 | Neural Style Transfer For Remote Sensing | MARIA KARATZOGLIDI et. al. | The purpose of this study is to present a method for creating artistic maps from satellite images, based on the NST algorithm. | CS.arxiv | 2020-07-31 |
| 268 | Heatmap-based Vanishing Point Boosts Lane Detection | YIN-BO LIU et. al. | In this paper, we proposed a new multi-task fusion network architecture for high-precision lane detection. | CS.arxiv | 2020-07-30 |
| 269 | Weakly Supervised Minirhizotron Image Segmentation With MIL-CAM | GUOHAO YU et. al. | We present a multiple instance learning class activation map (MIL-CAM) approach for pixel-level minirhizotron image segmentation given weak image-level labels. | CS.arxiv | 2020-07-30 |
| 270 | Growing Efficient Deep Networks By Structured Continuous Sparsification | XIN YUAN et. al. | We develop an approach to training deep networks while dynamically adjusting their architecture, driven by a principled combination of accuracy and sparsity objectives. | CS.arxiv | 2020-07-30 |
| 271 | Cascaded Non-local Neural Network For Point Cloud Semantic Segmentation | MINGMEI CHENG et. al. | In this paper, we propose a cascaded non-local neural network for point cloud segmentation. | CS.arxiv | 2020-07-30 |
| 272 | Linear Attention Mechanism: An Efficient Attention For Semantic Segmentation | RUI LI et. al. | In this paper, to remedy this deficiency, we propose a Linear Attention Mechanism which is approximate to dot-product attention with much less memory and computational costs. | CS.arxiv | 2020-07-29 |
| 273 | Learning To Pay Attention To Mistakes | MOU-CHENG XU et. al. | In this paper, we propose a novel attention mechanism to directly address such high false negative rates, called Paying Attention to Mistakes. | CS.arxiv | 2020-07-29 |
| 274 | Single Image Cloud Detection Via Multi-Image Fusion | SCOTT WORKMAN et. al. | In this work, we explore how recent advances in multi-image fusion can be leveraged to bootstrap single image cloud detection. To support the training and evaluation of our approach, we collect a large dataset of Sentinel-2 images along with a per-pixel semantic labelling for land cover. | CS.arxiv | 2020-07-29 |
| 275 | On The Impact Of Lossy Image And Video Compression On The Performance Of Deep Convolutional Neural Network Architectures | MATT POYSER et. al. | Whilst the reported performance of these approaches is impressive, this study investigates the hitherto unapproached question of the impact of commonplace image and video compression techniques on the performance of such deep learning architectures. | CS.arxiv | 2020-07-28 |
| 276 | Learning From Scale-Invariant Examples For Domain Adaptation In Semantic Segmentation | M. NASEER SUBHANI et. al. | In this paper, we propose a novel approach of exploiting scale-invariance property of the semantic segmentation model for self-supervised domain adaptation. | CS.arxiv | 2020-07-28 |
| 277 | Self-Prediction For Joint Instance And Semantic Segmentation Of Point Clouds | JINXIAN LIU et. al. | We develop a novel learning scheme named Self-Prediction for 3D instance and semantic segmentation of point clouds. | CS.arxiv | 2020-07-27 |
| 278 | Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations And Dataset Biases | SENTHIL PURUSHWALKAM et. al. | We demonstrate that approaches like MOCO and PIRL learn occlusion-invariant representations. | CS.arxiv | 2020-07-27 |
| 279 | Point-to-set Distance Functions For Weakly Supervised Segmentation | BAS PETERS | We present a new algorithm to include such information via constraints on the network output, implemented via projection-based point-to-set distance functions. | CS.arxiv | 2020-07-26 |
| 280 | MirrorNet: Bio-Inspired Adversarial Attack For Camouflaged Object Segmentation | JINNAN YAN et. al. | In this paper, we propose a novel bio-inspired network, named the MirrorNet, that leverages both instance segmentation and adversarial attack for the camouflaged object segmentation. | CS.arxiv | 2020-07-25 |
| 281 | Applying Semantic Segmentation To Autonomous Cars In The Snowy Environment | ZHAOYU PAN et. al. | We train the Fully Convolutional Networks (FCN) on our own dataset and present the experimental results. | CS.arxiv | 2020-07-25 |
| 282 | KPRNet: Improving Projection-based LiDAR Semantic Segmentation | DEYVID KOCHANOV et. al. | In this work, we adopt recent advances in both image and point cloud segmentation to achieve a better accuracy in the task of segmenting LiDAR scans. | CS.arxiv | 2020-07-24 |
| 283 | Greenhouse Segmentation On High-Resolution Optical Satellite Imagery Using Deep Learning Techniques | ORKHAN BAGHIRLI et. al. | In this paper, a sound methodology is proposed for pixel-wise classification on images acquired by the Azersky (SPOT-7) optical satellite. | CS.arxiv | 2020-07-22 |
| 284 | Real-Time Instrument Segmentation In Robotic Surgery Using Auxiliary Supervised Deep Adversarial Learning | MOBARAKOL ISLAM et. al. | We propose a multi-resolution feature fusion module (MFF) to fuse the feature maps of different dimensions and channels from the auxiliary and main branch. | CS.arxiv | 2020-07-22 |
| 285 | Weakly Supervised Few-shot Object Segmentation Using Co-Attention With Visual And Semantic Embeddings | MENNATULLAH SIAM et. al. | We propose a novel multi-modal interaction module for few-shot object segmentation that utilizes a co-attention mechanism using both visual and word embedding. | CS.ijcai | 2020-07-21 |
| 286 | Cross-denoising Network Against Corrupted Labels In Medical Image Segmentation With Domain Shift | QINMING ZHANG et. al. | In this paper, we propose a novel robust cross-denoising framework using two peer networks to address domain shift and corrupted label problems with a peer-review strategy. | CS.ijcai | 2020-07-21 |
| 287 | AinnoSeg: Panoramic Segmentation With High Perfomance | JIAHONG WU et. al. | Aiming to address these issues, this paper presents some useful tricks. | CS.arxiv | 2020-07-21 |
| 288 | SimPropNet: Improved Similarity Propagation For Few-shot Image Segmentation | SIDDHARTHA GAIROLA et. al. | In this work, we demonstrate gaps in the utilization of this similarity information in existing methods, and present a framework – SimPropNet, to bridge those gaps. | CS.ijcai | 2020-07-21 |
| 289 | Unsupervised Domain Adaptation With Dual-Scheme Fusion Network For Medical Image Segmentation | DANBING ZOU et. al. | In this paper, we propose an innovative Dual-Scheme Fusion Network (DSFN) for unsupervised domain adaptation. | CS.ijcai | 2020-07-21 |
| 290 | AttAN: Attention Adversarial Networks For 3D Point Cloud Semantic Segmentation | GEGE ZHANG et. al. | To address this problem, we first extend adversarial learning to this task and propose a novel framework Attention Adversarial Networks (AttAN). With high-order correlations in label sets learned from the adversarial learning, segmentation network can predict labels closer to the real ones and correct noisy results. | CS.ijcai | 2020-07-21 |
| 291 | A 3D Convolutional Approach To Spectral Object Segmentation In Space And Time | ELENA BURCEANU et. al. | We formulate object segmentation in video as a spectral graph clustering problem in space and time, in which nodes are pixels and their relations form local neighbourhoods. | CS.ijcai | 2020-07-21 |
| 292 | E3SN: Efficient End-to-End Siamese Network For Video Object Segmentation | MENG LAN et. al. | This paper proposes an efficient end-to-end Siamese network for VOS. | CS.ijcai | 2020-07-21 |
| 293 | SceneEncoder: Scene-Aware Semantic Segmentation Of Point Clouds With A Learnable Scene Descriptor | JIACHEN XU et. al. | In this paper, we propose a SceneEncoder module to impose a scene-aware guidance to enhance the effect of global information. | CS.ijcai | 2020-07-21 |
| 294 | Overflow Aware Quantization: Accelerating Neural Network Inference By Low-bit Multiply-Accumulate Operations | HONGWEI XIE et. al. | To address this problem, we propose an overflow aware quantization method by designing trainable adaptive fixed-point representation, to optimize the number of bits for each input tensor while prohibiting numeric overflow during the computation. | CS.ijcai | 2020-07-21 |
| 295 | BARNet: Bilinear Attention Network With Adaptive Receptive Fields For Surgical Instrument Segmentation | ZHEN-LIANG NI et. al. | In this paper, we propose a bilinear attention network with adaptive receptive fields to address these two issues. | CS.ijcai | 2020-07-21 |
| 296 | Shape-aware Semi-supervised 3D Semantic Segmentation For Medical Images | SHUAILIN LI et. al. | In this work, we propose a novel shapeaware semi-supervised segmentation strategy to leverage abundant unlabeled data and to enforce a geometric shape constraint on the segmentation output. | CS.arxiv | 2020-07-21 |
| 297 | Meta Segmentation Network For Ultra-Resolution Medical Images | TONG WU et. al. | However, the fusion structure in these methods require to be designed elaborately to achieve desirable result, which leads to model redundancy. In this paper, we propose Meta Segmentation Network (MSN) to solve this challenging problem. | CS.ijcai | 2020-07-21 |
| 298 | Self-Supervision With Superpixels: Training Few-shot Medical Image Segmentation Without Annotation | CHENG OUYANG et. al. | To address this problem we make several contributions: (1) A novel self-supervised FSS framework for medical images in order to eliminate the requirement for annotations during training. | CS.arxiv | 2020-07-20 |
| 299 | Can We Cover Navigational Perception Needs Of The Visually Impaired By Panoptic Segmentation? | WEI MAO et. al. | Motivated by that, we propose to utilize panoptic segmentation as an approach to navigating visually impaired people by offering both things and stuff awareness in the proximity of the visually impaired. | CS.arxiv | 2020-07-20 |
| 300 | Unsupervised Learning Of Image Segmentation Based On Differentiable Feature Clustering | WONJIK KIM et. al. | The contributions of this study are four-fold. | CS.arxiv | 2020-07-20 |
| 301 | Beyond Single Stage Encoder-Decoder Networks: Deep Decoders For Semantic Image Segmentation | GABRIEL L. OLIVEIRA et. al. | To address these limitations, we propose a new architecture based on a decoder which uses a set of shallow networks for capturing more information content. Additionally, we present a set of experiments augmenting semantic segmentation with optical flow information, showing that motion clues can boost pure image based semantic segmentation approaches. | CS.arxiv | 2020-07-19 |
| 302 | Towards Emergent Language Symbolic Semantic Segmentation And Model Interpretability | ALBERTO SANTAMARIA-PANG et. al. | Inspired by how humans communicate complex ideas through language, we developed a generalized Symbolic Semantic ($\text{S}^2$) framework for interpretable segmentation. | CS.arxiv | 2020-07-18 |
| 303 | Edge-Preserving Guided Semantic Segmentation For VIPriors Challenge | CHIH-CHUNG HSU et. al. | To overcome this shortcoming, therefore, we propose edge-preserving guidance to obtain the extra prior information, to avoid the overfitting under small-scale training dataset. | CS.arxiv | 2020-07-17 |
| 304 | Classes Matter: A Fine-grained Adversarial Approach To Cross-domain Semantic Segmentation | HAORAN WANG et. al. | To fully exploit the supervision in the source domain, we propose a fine-grained adversarial learning strategy for class-level feature alignment while preserving the internal structure of semantics across domains. | CS.arxiv | 2020-07-17 |
| 305 | Superpixel-Guided Label Softening For Medical Image Segmentation | HANG LI et. al. | In this paper, we propose superpixel-based label softening to tackle the above issue. | CS.arxiv | 2020-07-17 |
| 306 | DACS: Domain Adaptation Via Cross-domain Mixed Sampling | WILHELM TRANHEDEN et. al. | We propose DACS: Domain Adaptation via Cross-domain mixed Sampling, which mixes images from the two domains along with the corresponding labels. | CS.arxiv | 2020-07-16 |
| 307 | Efficient Full Image Interactive Segmentation By Leveraging Within-image Appearance Similarity | MYKHAYLO ANDRILUKA et. al. | We propose a new approach to interactive full-image semantic segmentation which enables quickly collecting training data for new datasets with previously unseen semantic classes (A demo is available at https://youtu.be/yUk8D5gEX-o). | CS.arxiv | 2020-07-16 |
| 308 | Autoregressive Unsupervised Image Segmentation | YASSINE OUALI et. al. | In this work, we propose a new unsupervised image segmentation approach based on mutual information maximization between different constructed views of the inputs. | CS.arxiv | 2020-07-16 |
| 309 | Multi-Task Pruning For Semantic Segmentation Networks | XINGHAO CHEN et. al. | Hence to identify the redundancy in segmentation networks, we present a multi-task channel pruning approach. | CS.arxiv | 2020-07-16 |
| 310 | Advances In Deep Learning For Hyperspectral Image Analysis–Addressing Challenges Arising In Practical Imaging Scenarios | XIONG ZHOU et. al. | In this chapter, we will review recent advances in the community that leverage deep learning for robust hyperspectral image analysis despite these unique challenges — specifically, we will review unsupervised, semi-supervised and active learning approaches to image analysis, as well as transfer learning approaches for multi-source (e.g. multi-sensor, or multi-temporal) image analysis. | CS.arxiv | 2020-07-16 |
| 311 | Complete & Label: A Domain Adaptation Approach To Semantic Segmentation Of LiDAR Point Clouds | LI YI et. al. | We study an unsupervised domain adaptation problem for the semantic labeling of 3D point clouds, with a particular focus on domain discrepancies induced by different LiDAR sensors. | CS.arxiv | 2020-07-16 |
| 312 | Anisotropic Mesh Adaptation For Image Segmentation Based On Mumford-Shah Functional | KARRAR ABBAS et. al. | In this paper, we consider image segmentation by solving a partial differentiation equation (PDE) model based on the Mumford-Shah functional. | CS.arxiv | 2020-07-16 |
| 313 | ClassMix: Segmentation-Based Data Augmentation For Semi-Supervised Learning | VIKTOR OLSSON et. al. | We propose a novel data augmentation mechanism called ClassMix, which generates augmentations by mixing unlabelled samples, by leveraging on the network’s predictions for respecting object boundaries. | CS.arxiv | 2020-07-15 |
| 314 | Negative Pseudo Labeling Using Class Proportion For Semantic Segmentation In Pathology | HIROKI TOKUNAGA et. al. | We propose a weakly-supervised cell tracking method that can train a convolutional neural network (CNN) by using only the annotation of cell detection (i.e., the coordinates of cell positions) without association information, in which cell positions can be easily obtained by nuclear staining. | CS.arxiv | 2020-07-15 |
| 315 | BUNET: Blind Medical Image Segmentation Based On Secure UNET | SONG BIAN et. al. | To ensure efficient machine learning as a service schemes while protecting data confidentiality, in this work, we propose blind UNET (BUNET), a secure protocol that implements privacy-preserving medical image segmentation based on the UNET architecture. | CS.arxiv | 2020-07-14 |
| 316 | Video Object Segmentation With Episodic Graph Memory Networks | XINKAI LU et. al. | In this work, a graph memory network is developed to address the novel idea of learning to update the segmentation model. | CS.arxiv | 2020-07-14 |
| 317 | ContourRend: A Segmentation Method For Improving Contours By Rendering | JUNWEN CHEN et. al. | In order to obtain fine contours, we propose a segmentation method named ContourRend which adopts a contour renderer to refine segmentation contours. | CS.arxiv | 2020-07-14 |
| 318 | Deep Heterogeneous Autoencoder For Subspace Clustering Of Sequential Data | ABUBAKAR SIDDIQUE et. al. | We propose an unsupervised learning approach using a convolutional and fully connected autoencoder, which we call deep heterogeneous autoencoder, to learn discriminative features from segmentation masks and detection bounding boxes. | CS.arxiv | 2020-07-14 |
| 319 | Self-Supervised Monocular Depth Estimation: Solving The Dynamic Object Problem By Semantic Guidance | MARVIN KLINGNER et. al. | In this work we present a new self-supervised semantically-guided depth estimation (SGDepth) method to deal with moving dynamic-class (DC) objects, such as moving cars and pedestrians, which violate the static-world assumptions typically made during training of such models. | CS.arxiv | 2020-07-14 |
| 320 | An Uncertainty-based Human-in-the-loop System For Industrial Tool Wear Analysis | ALEXANDER TREISS et. al. | To address these issues, we use uncertainty measures based on Monte-Carlo dropout in the context of a human-in-the-loop system to increase the system’s transparency and performance. | CS.arxiv | 2020-07-14 |
| 321 | Tackling The Problem Of Limited Data And Annotations In Semantic Segmentation | AHMADREZA JEDDI | In this work, the case of semantic segmentation on a small image dataset (simulated by 1000 randomly selected images from PASCAL VOC 2012), where only weak supervision signals (scribbles from user interaction) are available is studied. | CS.arxiv | 2020-07-14 |
| 322 | Automatic Image Labelling At Pixel Level | XIANG ZHANG et. al. | To alleviate the burden of manual image labelling, we propose an interesting learning approach to generate pixel-level image labellings automatically. | CS.arxiv | 2020-07-14 |
| 323 | Part-aware Prototype Network For Few-shot Semantic Segmentation | YONGFEI LIU et. al. | In this paper, we propose a novel few-shot semantic segmentation framework based on the prototype representation. | CS.arxiv | 2020-07-13 |
| 324 | Dual-Teacher: Integrating Intra-domain And Inter-domain Teachers For Annotation-efficient Cardiac Segmentation | KANG LI et. al. | In this paper, we aim to investigate the feasibility of simultaneously leveraging abundant unlabeled data and well-established cross-modality data for annotation-efficient medical image segmentation. | CS.arxiv | 2020-07-13 |
| 325 | On Uncertainty Estimation In Active Learning For Image Segmentation | BO LI et. al. | In this paper, we explore uncertainty calibration within an active learning framework for medical image segmentation, an area where labels often are scarce. | CS.arxiv | 2020-07-13 |
| 326 | SkyScapes — Fine-Grained Semantic Understanding Of Aerial Scenes | SEYED MAJID AZIMI et. al. | We therefore propose a novel multi-task model, which incorporates semantic edge detection and is better tuned for feature extraction from a wide range of scales. | CS.arxiv | 2020-07-12 |
| 327 | Self-Supervised Drivable Area And Road Anomaly Segmentation Using RGB-D Data For Robotic Wheelchairs | HENGLI WANG et. al. | We contribute to the solution of this problem for the task of drivable area and road anomaly segmentation by proposing a self-supervised learning approach. | CS.arxiv | 2020-07-12 |
| 328 | Fast Video Object Segmentation With Temporal Aggregation Network And Dynamic Template Matching | XUHUA HUANG et. al. | In this paper, we introduce tracking-by-detection into VOS which can coherently integrate segmentation into tracking, by proposing a new temporal aggregation network and a novel dynamic time-evolving template matching mechanism to achieve significantly improved performance. | CS.arxiv | 2020-07-11 |
| 329 | PCAMs: Weakly Supervised Semantic Segmentation Using Point Supervision | R. AUSTIN MCEVER et. al. | This paper presents a novel procedure for producing semantic segmentation from images given some point level annotations. | CS.arxiv | 2020-07-10 |
| 330 | ESA-ReID: Entropy-Based Semantic Feature Alignment For Person Re-ID | CHAOPING TU et. al. | In this paper we propose an entropy based semantic feature alignment model, which takes advantages of the detailed information of the human semantic feature. We construct a new re-ID dataset based on content videos with many cases of occlusion and body part missing, which will be released in future. | CS.arxiv | 2020-07-09 |
| 331 | Towards Unsupervised Learning For Instrument Segmentation In Robotic Surgery With Cycle-Consistent Adversarial Networks | DANIIL PAKHOMOV et. al. | Since generated annotations will not directly correspond to endoscopic images due to errors, we formulate the problem as an unpaired image-to-image translation where the goal is to learn the mapping between an input endoscopic image and a corresponding annotation using an adversarial model. | CS.arxiv | 2020-07-08 |
| 332 | A Multi-Level Approach To Waste Object Segmentation | TAO WANG et. al. | We address the problem of localizing waste objects from a color image and an optional depth image, which is a key perception component for robotic interaction with such objects. In addition, we create a new RGBD waste object segmentation dataset, MJU-Waste, that is made public to facilitate future research in this area. | CS.arxiv | 2020-07-08 |
| 333 | Superpixel Segmentation Using Dynamic And Iterative Spanning Forest | F. C. BELEM et. al. | In this work, we present Dynamic ISF (DISF) — a method based on the following steps. | CS.arxiv | 2020-07-08 |
| 334 | Real-time Semantic Segmentation With Fast Attention | PING HU et. al. | In this paper, we propose a novel architecture that addresses both challenges and achieves state-of-the-art performance for semantic segmentation of high-resolution images and videos in real-time. | CS.arxiv | 2020-07-07 |
| 335 | A Free Viewpoint Portrait Generator With Dynamic Styling | ANPEI CHEN et. al. | Therefore, we propose to decompose the generation space into two subspaces: geometric and texture space. | CS.arxiv | 2020-07-07 |
| 336 | Scribble-based Domain Adaptation Via Co-segmentation | REUBEN DORENT et. al. | In this work, we propose a novel weakly-supervised method. | CS.arxiv | 2020-07-07 |
| 337 | Meta Corrupted Pixels Mining For Medical Image Segmentation | JIXIN WANG et. al. | Aiming at training deep segmentation models on datasets with probably corrupted annotations, we propose a novel Meta Corrupted Pixels Mining (MCPM) method based on a simple meta mask network. | CS.arxiv | 2020-07-07 |
| 338 | Calibrated BatchNorm: Improving Robustness Against Noisy Weights In Neural Networks | LI-HUANG TSAI et. al. | In this paper, we propose to recalculate the statistics of the batch normalization layers to calibrate the biased distributions during the inference phase. | CS.arxiv | 2020-07-07 |
| 339 | Learning And Reasoning With The Graph Structure Representation In Robotic Surgery | MOBARAKOL ISLAM et. al. | For this purpose, we develop an approach to generate the scene graph and predict surgical interactions between instruments and surgical region of interest (ROI) during robot-assisted surgery. | CS.arxiv | 2020-07-07 |
| 340 | Leveraging Class Hierarchies With Metric-Guided Prototype Learning | VIVIEN SAINTE FARE GARNOT et. al. | We propose to integrate this metric in a new and versatile classification layer in order to model the disparity of errors. | CS.arxiv | 2020-07-06 |
| 341 | Image Stitching Based On Planar Region Consensus | AOCHENG LI et. al. | In this paper, noticing the importance of planar structure under perspective geometry, we propose a new image stitching method which stitches images by allowing for the alignment of a set of matched dominant planar regions. | CS.arxiv | 2020-07-06 |
| 342 | Edge Assisted Mobile Semantic Visual SLAM | J. XU ET AL. | In this paper we present the design, implementation, and evaluation of edgeSLAM, an edge assisted real-time semantic visual SLAM service running on mobile devices. | CS.infocom | 2020-07-06 |
| 343 | Exploration Of Optimized Semantic Segmentation Architectures For Edge-Deployment On Drones | VIVEK PARMAR et. al. | In this paper, we present an analysis on the impact of network parameters for semantic segmentation architectures in context of UAV data processing. | CS.arxiv | 2020-07-06 |
| 344 | Anatomical Data Augmentation Via Fluid-based Image Registration | ZHENGYANG SHEN et. al. | We introduce a fluid-based image augmentation method for medical image analysis. | CS.arxiv | 2020-07-05 |
| 345 | Complex Network Construction For Interactive Image Segmentation Using Particle Competition And Cooperation: A New Approach | JEFFERSON ANTONIO RIBEIRO PASSERINI et. al. | The present paper proposes the elimination of the weight vector through modifications in the network construction phase. | CS.arxiv | 2020-07-03 |
| 346 | A Discrete Probabilistic Approach To Dense Flow Visualization | DANIEL PREUSS et. al. | In this work, we examine a discrete formulation of dense flow visualization. | CS.arxiv | 2020-07-03 |
| 347 | Few-Shot Semantic Segmentation Augmented With Image-Level Weak Annotations | SHUO LEI et. al. | In this paper, we advance the few-shot segmentation paradigm towards a scenario where image-level annotations are available to help the training process of a few pixel-level annotations. | CS.arxiv | 2020-07-03 |
| 348 | PointTrack++ For Effective Online Multi-Object Tracking And Segmentation | ZHENBO XU et. al. | In this work, we present PointTrack++, an effective on-line framework for MOTS, which remarkably extends our recently proposed PointTrack framework. | CS.arxiv | 2020-07-03 |
| 349 | Evaluating Uncertainty Estimation Methods On 3D Semantic Segmentation Of Point Clouds | SWAROOP BHANDARY K et. al. | In this work, we evaluate three uncertainty quantification methods namely Deep Ensembles, MC-Dropout and MC-DropConnect on the DarkNet21Seg 3D semantic segmentation model and comprehensively analyze the impact of various parameters such as number of models in ensembles or forward passes, and drop probability values, on task performance and uncertainty estimate quality. | CS.arxiv | 2020-07-03 |
| 350 | Weakly Supervised Segmentation With Multi-scale Adversarial Attention Gates | GABRIELE VALVANO et. al. | We evaluated our model on several medical (ACDC, LVSC, CHAOS) and non-medical (PPSS) datasets, and we report performance levels matching those achieved by models trained with fully annotated segmentation masks. | CS.arxiv | 2020-07-02 |
| 351 | Globally Optimal Segmentation Of Mutually Interacting Surfaces Using Deep Learning | HUI XIE et. al. | In this work, we propose to parameterize the surface cost functions in the graph model and leverage DL to learn those parameters. | CS.arxiv | 2020-07-02 |
| 352 | The IKEA ASM Dataset: Understanding People Assembling Furniture Through Actions, Objects And Pose | YIZHAK BEN-SHABAT et. al. | To enable richer analysis and understanding of human activities, we introduce IKEA ASM—a three million frame, multi-view, furniture assembly video dataset that includes depth, atomic actions, object segmentation, and human pose. | CS.arxiv | 2020-07-01 |
| 353 | BiO-Net: Learning Recurrent Bi-directional Connections For Encoder-Decoder Architecture | TIANGE XIANG et. al. | To tackle this issue in such U-Net variants, in this paper, we present a novel Bi-directional O-shape network (BiO-Net) that reuses the building blocks in a recurrent manner without introducing any extra parameters. | CS.arxiv | 2020-07-01 |
| 354 | Weakly-Supervised Segmentation For Disease Localization In Chest X-Ray Images | OSTAP VINIAVSKYI et. al. | In this paper, we propose a novel approach to the semantic segmentation of medical chest X-ray images with only image-level class labels as supervision. | CS.arxiv | 2020-07-01 |
| 355 | TiledSoilingNet: Tile-level Soiling Detection On Automotive Surround-view Cameras Using Coverage Metric | ARINDAM DAS et. al. | We propose a novel method to regress the area of each soiling type within a tile directly. | CS.arxiv | 2020-07-01 |
| 356 | Learning Geocentric Object Pose In Oblique Monocular Images | GORDON CHRISTIE et. al. | We exploit these attributes to rectify oblique images and remove observed object parallax to dramatically improve the accuracy of localization and to enable accurate alignment of multiple images taken from very different oblique viewpoints. | CS.arxiv | 2020-07-01 |
| 357 | Learning Unbiased Zero-shot Semantic Segmentation Networks Via Transductive Transfer | HAIYANG LIU et. al. | In this paper, we propose an easy-to-implement transductive approach to alleviate the prediction bias in zero-shot semantic segmentation. | CS.arxiv | 2020-07-01 |
| 358 | A Fast Algorithm For Geodesic Active Contours With Applications To Medical Image Segmentation | JUN MA et. al. | In this paper, we use characteristic functions to implicitly approximate the contours, propose a new representation to the GAC and derive an efficient algorithm termed as the iterative convolution-thresholding method (ICTM). | CS.arxiv | 2020-07-01 |
| 359 | Robust Semantic Segmentation In Adverse Weather Conditions By Means Of Fast Video-Sequence Segmentation | ANDREAS PFEUFFER et. al. | Hence, in this work, the LSTM-ICNet is sped up by modifying the recurrent units of the network so that it becomes real-time capable again. | CS.arxiv | 2020-07-01 |
| 360 | Interactive Deep Refinement Network For Medical Image Segmentation | TITINUNT KITRUNGROTSAKUL et. al. | In this paper, we propose an interactive deep refinement framework to improve the traditional semantic segmentation networks such as U-Net and fully convolutional network. | CS.arxiv | 2020-06-27 |
| 362 | Suggestive Annotation Of Brain Tumour Images With Gradient-guided Sampling | CHENGLIANG DAI et. al. | In this paper, we propose an efficient annotation framework for brain tumour images that is able to suggest informative sample images for human experts to annotate. | CS.arxiv | 2020-06-26 |
| 363 | RPM-Net: Recurrent Prediction Of Motion And Parts From Point Cloud | ZIHAO YAN et. al. | We introduce RPM-Net, a deep learning-based approach which simultaneously infers movable parts and hallucinates their motions from a single, un-segmented, and possibly partial, 3D point cloud shape. | CS.arxiv | 2020-06-26 |
| 364 | Region-of-interest Guided Supervoxel Inpainting For Self-supervision | SUBHRADEEP KAYAL et. al. | In this work, we focus on image inpainting as the self-supervised proxy task, and propose two novel structural changes to further enhance the performance of a deep neural network. | CS.arxiv | 2020-06-26 |
| 365 | An Advert Creation System For 3D Product Placements | IVAN BACHER et. al. | This paper presents a Video Advertisement Placement & Integration (Adverts) framework, which is capable of perceiving the 3D geometry of the scene and camera motion to blend 3D virtual objects in videos and create the illusion of reality. | CS.arxiv | 2020-06-26 |
| 366 | Learning To Simulate Complex Scenes | ZHENFENG XUE et. al. | To optimize the attribute values and obtain a training set of similar content to real-world data, we propose a scalable discretization-and-relaxation (SDR) approach. | CS.arxiv | 2020-06-25 |
| 367 | Fully Convolutional Open Set Segmentation | HUGO OLIVEIRA et. al. | In this paper, we discuss the limitations of Closed Set segmentation and propose two fully convolutional approaches to effectively address Open Set semantic segmentation: OpenFCN and OpenPCS. | CS.arxiv | 2020-06-25 |
| 368 | ATSO: Asynchronous Teacher-Student Optimization For Semi-Supervised Medical Image Segmentation | XINYUE HUO et. al. | To alleviate this issue, we propose ATSO, an asynchronous version of teacher-student optimization. | CS.arxiv | 2020-06-24 |
| 369 | Post-DAE: Anatomically Plausible Segmentation Via Post-Processing With Denoising Autoencoders | AGOSTINA J LARRAZABAL et. al. | We introduce Post-DAE, a post-processing method based on denoising autoencoders (DAE) to improve the anatomical plausibility of arbitrary biomedical image segmentation algorithms. | CS.arxiv | 2020-06-24 |
| 370 | Improving Task-specific Representation Via 1M Unlabelled Images Without Any Extra Knowledge | AAYUSH BANSAL | We propose an exceedingly simple method of conditioning an existing representation on a diverse data distribution and observe that a model trained on diverse examples acts as a better initialization. | CS.arxiv | 2020-06-24 |
| 371 | Affinity Fusion Graph-based Framework For Natural Image Segmentation | YANG ZHANG et. al. | This paper proposes an affinity fusion graph framework to effectively connect different graphs with highly discriminating power and nonlinearity for natural image segmentation. | CS.arxiv | 2020-06-24 |
| 372 | Calibrated Adversarial Refinement For Multimodal Semantic Segmentation | ELIAS KASSAPIS et. al. | In this work, we aim to learn a calibrated multimodal predictive distribution, where the empirical frequency of the sampled predictions closely reflects that of the corresponding labels in the training set. | CS.arxiv | 2020-06-23 |
| 373 | Road Surface Detection And Differentiation Considering Surface Damages | THIAGO RATEKE et. al. | Road Surface Detection And Differentiation Considering Surface Damages | CS.arxiv | 2020-06-23 |
| 374 | Non-parametric Spatially Constrained Local Prior For Scene Parsing On Real-world Data | LIGANG ZHANG | In this paper, we present the non-parametric Spatially Constrained Local Prior (SCLP) for scene parsing on realistic data. | CS.arxiv | 2020-06-23 |
| 375 | Deep Learning Of Unified Region, Edge, And Contour Models For Automated Image Segmentation | ALI HATAMIZADEH | In this thesis, we devise novel methodologies that address these issues and establish robust representation learning frameworks for fully-automatic semantic segmentation in medical imaging and mainstream computer vision. | CS.arxiv | 2020-06-22 |
| 376 | LAMP: Large Deep Nets With Automated Model Parallelism For Image Segmentation | WENTAO ZHU et. al. | In this work, we introduce Large deep 3D ConvNets with Automated Model Parallelism (LAMP) and investigate the impact of both input’s and deep 3D ConvNets’ size on segmentation accuracy. | CS.arxiv | 2020-06-22 |
| 377 | Auxiliary Learning By Implicit Differentiation | AVIV NAVON et. al. | We propose a novel framework, AuxiLearn, that targets both challenges, based on implicit differentiation. | CS.arxiv | 2020-06-22 |
| 378 | Self-supervised Video Object Segmentation | FANGRUI ZHU et. al. | The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a.k.a. dense tracking). | CS.arxiv | 2020-06-22 |
| 379 | Differentiable Rendering: A Survey | HIROHARU KATO et. al. | This paper reviews existing literature and discusses the current state of differentiable rendering, its applications and open research problems. | CS.arxiv | 2020-06-22 |
| 380 | Learning Physical Graph Representations From Visual Scenes | DANIEL M. BEAR et. al. | 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. | CS.arxiv | 2020-06-22 |
| 381 | Few-shot 3D Point Cloud Semantic Segmentation | NA ZHAO et. al. | To mitigate these limitations, we propose a novel attention-aware multi-prototype transductive few-shot point cloud semantic segmentation method to segment new classes given a few labeled examples. | CS.arxiv | 2020-06-22 |
| 382 | Kiwifruit Detection In Challenging Conditions | MAHLA NEJATI et. al. | This paper presents a semantic segmentation approach with two novel image prepossessing techniques designed to detect kiwifruit under the harsh lighting conditions found in the canopy. | CS.arxiv | 2020-06-21 |
| 383 | G-image Segmentation: Similarity-preserving Fuzzy C-Means With Spatial Information Constraint In Wavelet Space | CONG WANG et. al. | This work elaborates a similarity-preserving Fuzzy C-Means (FCM) algorithm for G-image segmentation and aims to develop techniques and tools for segmenting G-images. | CS.arxiv | 2020-06-20 |
| 384 | Adversarial Transfer Of Pose Estimation Regression | BORIS CHIDLOVSKII ASSEM SADEK | We identify the dataset shift an important barrier to generalization and consider transfer learning as an alternative way towards a better reuse of pose estimation models. | CS.arxiv | 2020-06-20 |
| 385 | Pyramidal Convolution: Rethinking Convolutional Neural Networks For Visual Recognition | IONUT COSMIN DUTA et. al. | This work introduces pyramidal convolution (PyConv), which is capable of processing the input at multiple filter scales. | CS.arxiv | 2020-06-20 |
| 386 | Adaptive Feature Recombination And Recalibration For Semantic Segmentation With Fully Convolutional Networks | SERGIO PEREIRA et. al. | In this paper, we propose recombination of features and a spatially adaptive recalibration block that is adapted for semantic segmentation with Fully Convolutional Networks – the SegSE block. | CS.arxiv | 2020-06-19 |
| 387 | Lookahead Adversarial Semantic Segmentation | HADI JAMALI-RAD et. al. | To battle the stability issues, we introduce a novel lookahead adversarial learning (LoAd) approach with an embedded label map aggregation module. | CS.arxiv | 2020-06-19 |
| 388 | AutoOD: Automated Outlier Detection Via Curiosity-guided Search And Self-imitation Learning | YUENING LI et. al. | To bridge the gap, in this paper, we propose AutoOD, an automated outlier detection framework, which aims to search for an optimal neural network model within a predefined search space. | CS.arxiv | 2020-06-19 |
| 389 | Video Panoptic Segmentation | DAHUN KIM et. al. | In this paper, we propose and explore a new video extension of this task, called video panoptic segmentation. | CS.arxiv | 2020-06-19 |
| 390 | BEV-Seg: Bird’s Eye View Semantic Segmentation Using Geometry And Semantic Point Cloud | MONG H. NG et. al. | In this work, we focus on bird’s eye semantic segmentation, a task that predicts pixel-wise semantic segmentation in BEV from side RGB images. | CS.arxiv | 2020-06-19 |
| 391 | Unsupervised Image Classification For Deep Representation Learning | WEIJIE CHEN et. al. | In this work, we aim to make this framework more simple and elegant without performance decline. | CS.arxiv | 2020-06-19 |
| 392 | Contrastive Learning Of Global And Local Features For Medical Image Segmentation With Limited Annotations | KRISHNA CHAITANYA et. al. | 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. | CS.arxiv | 2020-06-18 |
| 393 | Learning High-Resolution Domain-Specific Representations With A GAN Generator | DANIL GALEEV et. al. | In this work we study representations learnt by a GAN generator. | CS.arxiv | 2020-06-18 |
| 394 | Learnable Bernoulli Dropout For Bayesian Deep Learning | SHAHIN BOLUKI et. al. | In this work, we propose learnable Bernoulli dropout (LBD), a new model-agnostic dropout scheme that considers the dropout rates as parameters jointly optimized with other model parameters. | CS.aistats | 2020-06-18 |
| 395 | Video Semantic Segmentation With Distortion-Aware Feature Correction | JIAFAN ZHUANG et. al. | In this paper, we propose distortion-aware feature correction to alleviate the issue, which improves video segmentation performance by correcting distorted propagated features. | CS.arxiv | 2020-06-18 |
| 396 | SceneAdapt: Scene-based Domain Adaptation For Semantic Segmentation Using Adversarial Learning | DANIELE DI MAURO et. al. | As a first approach to address this challenging task, we propose SceneAdapt, a method for scene adaptation of semantic segmentation algorithms based on adversarial learning. We formalize this problem as a domain adaptation task and introduce a novel dataset of urban scenes with the related semantic labels. | CS.arxiv | 2020-06-18 |
| 397 | Video Moment Localization Using Object Evidence And Reverse Captioning | MADHAWA VIDANAPATHIRANA et. al. | We propose Multi-faceted VideoMoment Localizer (MML), an extension of MAC model by the introduction of visual object evidence via object segmentation masks and video understanding features via video captioning. | CS.arxiv | 2020-06-17 |
| 398 | StatAssist & GradBoost: A Study On Optimal INT8 Quantization-aware Training From Scratch | TAEHOON KIM et. al. | Here, we propose critical but straightforward optimization methods which enable the scratch training: floating-point statistic assisting (StatAssist) and stochastic-gradient boosting (GradBoost). | CS.arxiv | 2020-06-17 |
| 399 | FISHING Net: Future Inference Of Semantic Heatmaps In Grids | NOURELDIN HENDY et. al. | In this work, we present an end-to-end pipeline that performs semantic segmentation and short term prediction using a top-down representation. | CS.arxiv | 2020-06-17 |
| 400 | Evaluation Of 3D CNN Semantic Mapping For Rover Navigation | SEBASTIANO CHIODINI et. al. | In this work we present a technique to generate accurate three-dimensional semantic maps for Martian environment. | CS.arxiv | 2020-06-17 |
| 401 | Fast Object Classification And Meaningful Data Representation Of Segmented Lidar Instances | LUKAS HAHN et. al. | In this work, we propose a way to facilitate real-time Lidar object classification on CPU. | CS.arxiv | 2020-06-17 |
| 402 | Deep Learning Based Segmentation Of Fish In Noisy Forward Looking MBES Images | JESPER HAAHR CHRISTENSEN et. al. | In this work, we investigate a Deep Learning (DL) approach to fish segmentation in a small dataset of noisy low-resolution images generated by a forward-looking multibeam echosounder (MBES). | CS.arxiv | 2020-06-16 |
| 403 | ESL: Entropy-guided Self-supervised Learning For Domain Adaptation In Semantic Segmentation | ANTOINE SAPORTA et. al. | In this work, we propose Entropy-guided Self-supervised Learning (ESL), leveraging entropy as the confidence indicator for producing more accurate pseudo-labels. | CS.arxiv | 2020-06-15 |
| 405 | Multiscale Deep Equilibrium Models | SHAOJIE BAI et. al. | We propose a new class of implicit networks, the multiscale deep equilibrium model (MDEQ), suited to large-scale and highly hierarchical pattern recognition domains. | CS.arxiv | 2020-06-15 |
| 406 | Cardiac Segmentation With Strong Anatomical Guarantees | NATHAN PAINCHAUD et. al. | In this paper, we present a framework for producing cardiac image segmentation maps that are guaranteed to respect pre-defined anatomical criteria, while remaining within the inter-expert variability. | CS.arxiv | 2020-06-15 |
| 407 | A Generalized Asymmetric Dual-front Model For Active Contours And Image Segmentation | DA~CHEN et. al. | In this paper, we introduce a new type of geodesic metrics that encodes the edge-based anisotropy features, the region-based homogeneity penalization and asymmetric enhancement. | CS.arxiv | 2020-06-14 |
| 408 | Multi-Miner: Object-Adaptive Region Mining For Weakly-Supervised Semantic Segmentation | KUANGQI ZHOU et. al. | In this paper, we propose a novel multi-miner framework to perform a region mining process that adapts to diverse object sizes and is thus able to mine more integral and finer object regions. | CS.arxiv | 2020-06-14 |
| 409 | Split-Merge Pooling | OMID HOSSEINI JAFARI et. al. | In this work, we introduce Split-Merge pooling to fully preserve the spatial information without any subsampling. | CS.arxiv | 2020-06-13 |
| 410 | FCOS: A Simple And Strong Anchor-free Object Detector | ZHI TIAN et. al. | Here we propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to other dense prediction problems such as semantic segmentation. | CS.arxiv | 2020-06-13 |
| 411 | NoPeopleAllowed: The Three-Step Approach To Weakly Supervised Semantic Segmentation | MARIIA DOBKO et. al. | We propose a novel approach to weakly supervised semantic segmentation, which consists of three consecutive steps. | CS.arxiv | 2020-06-13 |
| 412 | Disentangled Non-Local Neural Networks | MINGHAO YIN et. al. | Based on these findings, we present the disentangled non-local block, where the two terms are decoupled to facilitate learning for both terms. | CS.arxiv | 2020-06-11 |
| 413 | Transferring And Regularizing Prediction For Semantic Segmentation | YIHENG ZHANG et. al. | In this paper, we novelly exploit the intrinsic properties of semantic segmentation to alleviate such problem for model transfer. | CS.arxiv | 2020-06-11 |
| 414 | Spectral Image Segmentation With Global Appearance Modeling | JEOVA F. S. ROCHA NETO et. al. | We introduce a new spectral method for image segmentation that incorporates long range relationships for global appearance modeling. | CS.arxiv | 2020-06-11 |
| 415 | Real-Time Video Inference On Edge Devices Via Adaptive Model Streaming | MEHRDAD KHANI et. al. | In this paper we propose Adaptive Model Streaming (AMS), a cloud-assisted approach to real-time video inference on edge devices. | CS.arxiv | 2020-06-11 |
| 416 | Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty | MIGUEL MONTEIRO et. al. | In this paper, we introduce stochastic segmentation networks (SSNs), an efficient probabilistic method for modelling aleatoric uncertainty with any image segmentation network architecture. | CS.arxiv | 2020-06-10 |
| 417 | Geometry-Aware Segmentation Of Remote Sensing Images Via Implicit Height Estimation | XIANG LI et. al. | To alleviate this data constraint and also take advantage of 3D elevation information, in this paper, we introduce a geometry-aware segmentation model that achieves accurate semantic labeling of aerial images via joint height estimation. | CS.arxiv | 2020-06-10 |
| 418 | Searching Learning Strategy With Reinforcement Learning For 3D Medical Image Segmentation | DONG YANG et. al. | Nevertheless, to fully exploit the potentials of neural networks, we propose an automated searching approach for the optimal training strategy with reinforcement learning. | CS.arxiv | 2020-06-10 |
| 419 | Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation On Point Clouds | JIACHENG WEI et. al. | In this paper, we propose a weakly supervised approach to predict point-level results using weak labels on 3D point clouds. | CS.cvpr | 2020-06-08 |
| 420 | Fast Template Matching And Update For Video Object Tracking And Segmentation | MINGJIE SUN et. al. | In this paper, the main task we aim to tackle is the multi-instance semi-supervised video object segmentation across a sequence of frames where only the first-frame box-level ground-truth is provided. | CS.cvpr | 2020-06-08 |
| 421 | Super-BPD: Super Boundary-to-Pixel Direction For Fast Image Segmentation | JIANQIANG WAN et. al. | In this paper, we propose a fast image segmentation method based on a novel super boundary-to-pixel direction (super-BPD) and a customized segmentation algorithm with super-BPD. | CS.cvpr | 2020-06-08 |
| 422 | Enhancing Cross-Task Black-Box Transferability Of Adversarial Examples With Dispersion Reduction | YANTAO LU et. al. | Our proposed attack minimizes the dispersion of the internal feature map, overcoming the limitations of existing attacks, that require task-specific loss functions and/or probing a target model. | CS.cvpr | 2020-06-08 |
| 423 | Interactive Image Segmentation With First Click Attention | ZHENG LIN et. al. | In this paper, we demonstrate the critical role of the first click about providing the location and main body information of the target object. | CS.cvpr | 2020-06-08 |
| 424 | Meta-Learning Of Neural Architectures For Few-Shot Learning | THOMAS ELSKEN et. al. | To improve upon this, we propose MetaNAS, the first method which fully integrates NAS with gradient-based meta-learning. | CS.cvpr | 2020-06-08 |
| 425 | Probabilistic Pixel-Adaptive Refinement Networks | ANNE S. WANNENWETSCH et. al. | We introduce probabilistic pixel-adaptive convolutions (PPACs), which not only depend on image guidance data for filtering, but also respect the reliability of per-pixel predictions. | CS.cvpr | 2020-06-08 |
| 426 | Deep Structure-Revealed Network For Texture Recognition | WEI ZHAI et. al. | To address this problem, we propose a novel Deep Structure-Revealed Network (DSR-Net) that leverages spatial dependency among the captured primitives as structural representation for texture recognition. | CS.cvpr | 2020-06-08 |
| 427 | Modeling The Background For Incremental Learning In Semantic Segmentation | FABIO CERMELLI et. al. | In this work we revisit classical incremental learning methods, proposing a new distillation-based framework which explicitly accounts for this shift. | CS.cvpr | 2020-06-08 |
| 428 | Squeeze-and-Attention Networks For Semantic Segmentation | ZILONG ZHONG et. al. | In this paper, we propose a novel squeeze-and-attention network (SANet) architecture that leverages an effective squeeze-and-attention (SA) module to account for two distinctive characteristics of segmentation: i) pixel-group attention, and ii) pixel-wise prediction. | CS.cvpr | 2020-06-08 |
| 429 | Bi-Directional Relationship Inferring Network For Referring Image Segmentation | ZHIWEI HU et. al. | In this work, we propose a bi-directional relationship inferring network (BRINet) to model the dependencies of cross-modal information. | CS.cvpr | 2020-06-08 |
| 430 | Dual Super-Resolution Learning For Semantic Segmentation | LI WANG et. al. | In this paper, we propose a simple and flexible two-stream framework named Dual Super-Resolution Learning (DSRL) to effectively improve the segmentation accuracy without introducing extra computation costs. | CS.cvpr | 2020-06-08 |
| 431 | Self-Supervised Equivariant Attention Mechanism For Weakly Supervised Semantic Segmentation | YUDE WANG et. al. | In this paper, we propose a self-supervised equivariant attention mechanism (SEAM) to discover additional supervision and narrow the gap. | CS.cvpr | 2020-06-08 |
| 432 | Deep Grouping Model For Unified Perceptual Parsing | ZHIHENG LI et. al. | Overcoming these challenges, we propose a deep grouping model (DGM) that tightly marries the two types of representations and defines a bottom-up and a top-down process for feature exchanging. | CS.cvpr | 2020-06-08 |
| 433 | Boundary-Aware 3D Building Reconstruction From A Single Overhead Image | JISAN MAHMUD et. al. | We propose a boundary-aware multi-task deep-learning-based framework for fast 3D building modeling from a single overhead image. | CS.cvpr | 2020-06-08 |
| 434 | Interactive Object Segmentation With Inside-Outside Guidance | SHIYIN ZHANG et. al. | To achieve this, we propose an Inside-Outside Guidance (IOG) approach in this work. | CS.cvpr | 2020-06-08 |
| 435 | Cross-Domain Correspondence Learning For Exemplar-Based Image Translation | PAN ZHANG et. al. | We present a general framework for exemplar-based image translation, which synthesizes a photo-realistic image from the input in a distinct domain (e.g., semantic segmentation mask, or edge map, or pose keypoints), given an exemplar image. | CS.cvpr | 2020-06-08 |
| 436 | FPConv: Learning Local Flattening For Point Convolution | YIQUN LIN et. al. | We introduce FPConv, a novel surface-style convolution operator designed for 3D point cloud analysis. | CS.cvpr | 2020-06-08 |
| 437 | Semi-Supervised Semantic Image Segmentation With Self-Correcting Networks | MOSTAFA S. IBRAHIM et. al. | In this paper, we introduce a principled semi-supervised framework that only use a small set of fully supervised images (having semantic segmentation labels and box labels) and a set of images with only object bounding box labels (we call it the weak-set). | CS.cvpr | 2020-06-08 |
| 438 | Computing Valid P-Values For Image Segmentation By Selective Inference | KOSUKE TANIZAKI et. al. | To overcome this difficulty, we introduce a statistical approach called selective inference, and develop a framework for computing valid p-values in which segmentation bias is properly accounted for. | CS.cvpr | 2020-06-08 |
| 439 | Iteratively-Refined Interactive 3D Medical Image Segmentation With Multi-Agent Reinforcement Learning | XUAN LIAO et. al. | We here propose to model the dynamic process of iterative interactive image segmentation as a Markov decision process (MDP) and solve it with reinforcement learning (RL). | CS.cvpr | 2020-06-08 |
| 440 | Foreground-Aware Relation Network For Geospatial Object Segmentation In High Spatial Resolution Remote Sensing Imagery | ZHUO ZHENG et. al. | 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. | CS.cvpr | 2020-06-08 |
| 441 | MSeg: A Composite Dataset For Multi-Domain Semantic Segmentation | JOHN LAMBERT et. al. | We present MSeg, a composite dataset that unifies se- mantic segmentation datasets from different domains. | CS.cvpr | 2020-06-08 |
| 442 | What Can Be Transferred: Unsupervised Domain Adaptation For Endoscopic Lesions Segmentation | JIAHUA DONG et. al. | To address these challenges, we develop a new unsupervised semantic transfer model including two complementary modules (i.e., T_D and T_F ) for endoscopic lesions segmentation, which can alternatively determine where and how to explore transferable domain-invariant knowledge between labeled source lesions dataset (e.g., gastroscope) and unlabeled target diseases dataset (e.g., enteroscopy). | CS.cvpr | 2020-06-08 |
| 443 | Nonparametric Object And Parts Modeling With Lie Group Dynamics | DAVID S. HAYDEN et. al. | Here, we relax such strong assumptions via an unsupervised, Bayesian nonparametric parts model that infers an unknown number of parts with motions coupled by a body dynamic and parameterized by SE(D), the Lie group of rigid transformations. | CS.cvpr | 2020-06-08 |
| 444 | PointPainting: Sequential Fusion For 3D Object Detection | SOURABH VORA et. al. | In this work, we propose PointPainting: a sequential fusion method to fill this gap. | CS.cvpr | 2020-06-08 |
| 445 | Deep Polarization Cues For Transparent Object Segmentation | AGASTYA KALRA et. al. | This paper reframes the problem of transparent object segmentation into the realm of light polarization, i.e., the rotation of light waves. | CS.cvpr | 2020-06-08 |
| 446 | Memory Aggregation Networks For Efficient Interactive Video Object Segmentation | JIAXU MIAO et. al. | In this work, we propose a unified framework, named Memory Aggregation Networks (MA-Net), to address the challenging iVOS in a more efficient way. | CS.cvpr | 2020-06-08 |
| 447 | Joint Semantic Segmentation And Boundary Detection Using Iterative Pyramid Contexts | MINGMIN ZHEN et. al. | In this paper, we present a joint multi-task learning framework for semantic segmentation and boundary detection. | CS.cvpr | 2020-06-08 |
| 448 | Scalable Uncertainty For Computer Vision With Functional Variational Inference | EDUARDO D. C. CARVALHO et. al. | By leveraging the structure of the induced covariance matrices, we propose numerically efficient algorithms which enable fast training in the context of high-dimensional tasks such as depth estimation and semantic segmentation. | CS.cvpr | 2020-06-08 |
| 449 | LT-Net: Label Transfer By Learning Reversible Voxel-Wise Correspondence For One-Shot Medical Image Segmentation | SHUXIN WANG et. al. | We introduce a one-shot segmentation method to alleviate the burden of manual annotation for medical images. | CS.cvpr | 2020-06-08 |
| 450 | PolarNet: An Improved Grid Representation For Online LiDAR Point Clouds Semantic Segmentation | YANG ZHANG et. al. | The combination of the aforementioned challenges motivates us to propose a new LiDAR-specific, KNN-free segmentation algorithm – PolarNet. | CS.cvpr | 2020-06-08 |
| 451 | Big GANs Are Watching You: Towards Unsupervised Object Segmentation With Off-the-Shelf Generative Models | ANDREY VOYNOV et. al. | In this work, we introduce an alternative, much simpler way to exploit generative models for unsupervised object segmentation. | CS.arxiv | 2020-06-08 |
| 452 | Sparse Layered Graphs For Multi-Object Segmentation | NIELS JEPPESEN et. al. | We introduce the novel concept of a Sparse Layered Graph (SLG) for s-t graph cut segmentation of image data. | CS.cvpr | 2020-06-08 |
| 453 | BANet: Bidirectional Aggregation Network With Occlusion Handling For Panoptic Segmentation | YIFENG CHEN et. al. | Motivated by these observations, we propose a novel deep panoptic segmentation scheme based on a bidirectional learning pipeline. | CS.cvpr | 2020-06-08 |
| 454 | A Transductive Approach For Video Object Segmentation | YIZHUO ZHANG et. al. | To address this issue, we propose a simple yet strong transductive method, in which additional modules, datasets, and dedicated architectural designs are not needed. | CS.cvpr | 2020-06-08 |
| 455 | Structure Boundary Preserving Segmentation For Medical Image With Ambiguous Boundary | HONG JOO LEE et. al. | In this paper, we propose a novel image segmentation method to tackle two critical problems of medical image, which are (i) ambiguity of structure boundary in the medical image domain and (ii) uncertainty of the segmented region without specialized domain knowledge. | CS.cvpr | 2020-06-08 |
| 456 | Pixel Consensus Voting For Panoptic Segmentation | HAOCHEN WANG et. al. | The core of our approach, Pixel Consensus Voting, is a framework for instance segmentation based on the generalized Hough transform. | CS.cvpr | 2020-06-08 |
| 457 | Context Prior For Scene Segmentation | CHANGQIAN YU et. al. | In this work, we directly supervise the feature aggregation to distinguish the intra-class and interclass context clearly. | CS.cvpr | 2020-06-08 |
| 458 | Learning A Weakly-Supervised Video Actor-Action Segmentation Model With A Wise Selection | JIE CHEN et. al. | To overcome these challenges, we propose a general Weakly-Supervised framework with a Wise Selection of training samples and model evaluation criterion (WS^2). | CS.cvpr | 2020-06-08 |
| 459 | Video To Events: Recycling Video Datasets For Event Cameras | DANIEL GEHRIG et. al. | In this paper, we present a method that addresses these needs by converting any existing video dataset recorded with conventional cameras to synthetic event data. | CS.cvpr | 2020-06-08 |
| 460 | Spatial Pyramid Based Graph Reasoning For Semantic Segmentation | XIA LI et. al. | In this paper, we apply graph convolution into the semantic segmentation task and propose an improved Laplacian. | CS.cvpr | 2020-06-08 |
| 461 | FDA: Fourier Domain Adaptation For Semantic Segmentation | YANCHAO YANG et. al. | We describe a simple method for unsupervised domain adaptation, whereby the discrepancy between the source and target distributions is reduced by swapping the low-frequency spectrum of one with the other. | CS.cvpr | 2020-06-08 |
| 462 | Semi-Supervised Semantic Segmentation With Cross-Consistency Training | YASSINE OUALI et. al. | In this paper, we present a novel cross-consistency based semi-supervised approach for semantic segmentation. | CS.cvpr | 2020-06-08 |
| 463 | Boosting Semantic Human Matting With Coarse Annotations | JINLIN LIU et. al. | In this paper, we propose to leverage coarse annotated data coupled with fine annotated data to boost end-to-end semantic human matting without trimaps as extra input. | CS.cvpr | 2020-06-08 |
| 464 | Footprints And Free Space From A Single Color Image | JAMIE WATSON et. al. | We introduce a model to predict the geometry of both visible and occluded traversable surfaces, given a single RGB image as input. | CS.cvpr | 2020-06-08 |
| 465 | XMUDA: Cross-Modal Unsupervised Domain Adaptation For 3D Semantic Segmentation | MAXIMILIAN JARITZ et. al. | In this work, we explore how to learn from multi-modality and propose cross-modal UDA (xMUDA) where we assume the presence of 2D images and 3D point clouds for 3D semantic segmentation. | CS.cvpr | 2020-06-08 |
| 466 | Semantics-Driven Unsupervised Learning For Monocular Depth And Ego-Motion Estimation | XIAOBIN WEI et. al. | We propose a semantics-driven unsupervised learning approach for monocular depth and ego-motion estimation from videos in this paper. | CS.arxiv | 2020-06-08 |
| 467 | Variational Context-Deformable ConvNets For Indoor Scene Parsing | ZHITONG XIONG et. al. | Thus, in this paper, we propose a novel variational context-deformable (VCD) module to learn adaptive receptive-field in a structured fashion. | CS.cvpr | 2020-06-08 |
| 468 | FibeR-CNN: Expanding Mask R-CNN To Improve Image-Based Fiber Analysis | MAX FREI et. al. | We therefore propose the use of region-based convolutional neural networks (R-CNNs) to automate this task. | CS.arxiv | 2020-06-08 |
| 469 | Learning Video Object Segmentation From Unlabeled Videos | XIANKAI LU et. al. | We propose a new method for video object segmentation (VOS) that addresses object pattern learning from unlabeled videos, unlike most existing methods which rely heavily on extensive annotated data. | CS.cvpr | 2020-06-08 |
| 470 | Learning Texture Invariant Representation For Domain Adaptation Of Semantic Segmentation | MYEONGJIN KIM et. al. | In this paper, considering the fundamental difference between the two domains as the texture, we propose a method to adapt to the target domain’s texture. | CS.cvpr | 2020-06-08 |
| 471 | The Edge Of Depth: Explicit Constraints Between Segmentation And Depth | SHENGJIE ZHU et. al. | In this work we study the mutual benefits of two common computer vision tasks, self-supervised depth estimation and semantic segmentation from images. | CS.cvpr | 2020-06-08 |
| 472 | Learning Instance Occlusion For Panoptic Segmentation | JUSTIN LAZAROW et. al. | To resolve this issue, we propose a branch that is tasked with modeling how two instance masks should overlap one another as a binary relation. | CS.cvpr | 2020-06-08 |
| 473 | Graph-Guided Architecture Search For Real-Time Semantic Segmentation | PEIWEN LIN et. al. | In order to release researchers from these tedious mechanical trials, we propose a Graph-guided Architecture Search (GAS) pipeline to automatically search real-time semantic segmentation networks. | CS.cvpr | 2020-06-08 |
| 474 | Fusion-Aware Point Convolution For Online Semantic 3D Scene Segmentation | JIAZHAO ZHANG et. al. | We propose a novel fusion-aware 3D point convolution which operates directly on the geometric surface being reconstructed and exploits effectively the inter-frame correlation for high-quality 3D feature learning. | CS.cvpr | 2020-06-08 |
| 475 | Advisable Learning For Self-Driving Vehicles By Internalizing Observation-to-Action Rules | JINKYU KIM et. al. | We propose a new approach that learns vehicle control with the help of human advice. | CS.cvpr | 2020-06-08 |
| 476 | Learning Dynamic Routing For Semantic Segmentation | YANWEI LI et. al. | This paper studies a conceptually new method to alleviate the scale variance in semantic representation, named dynamic routing. | CS.cvpr | 2020-06-08 |
| 477 | D3S – A Discriminative Single Shot Segmentation Tracker | ALAN LUKEZIC et. al. | We propose a discriminative single-shot segmentation tracker – D3S, which narrows the gap between visual object tracking and video object segmentation. | CS.cvpr | 2020-06-08 |
| 478 | Real-Time Panoptic Segmentation From Dense Detections | RUI HOU et. al. | In this paper, we propose a new single-shot panoptic segmentation network that leverages dense detections and a global self-attention mechanism to operate in real-time with performance approaching the state of the art. | CS.cvpr | 2020-06-08 |
| 479 | Computing The Testing Error Without A Testing Set | CIPRIAN A. CORNEANU et. al. | Here, we derive an algorithm to estimate the performance gap between training and testing without the need of a testing dataset. | CS.cvpr | 2020-06-08 |
| 480 | Learning 3D Semantic Scene Graphs From 3D Indoor Reconstructions | JOHANNA WALD et. al. | In our work we focus on scene graphs, a data structure that organizes the entities of a scene in a graph, where objects are nodes and their relationships modeled as edges. | CS.cvpr | 2020-06-08 |
| 481 | C2FNAS: Coarse-to-Fine Neural Architecture Search For 3D Medical Image Segmentation | QIHANG YU et. al. | In this paper, we propose a coarse-to-fine neural architecture search (C2FNAS) to automatically search a 3D segmentation network from scratch without inconsistency on network size or input size. | CS.cvpr | 2020-06-08 |
| 482 | Towards Photo-Realistic Virtual Try-On By Adaptively Generating-Preserving Image Content | HAN YANG et. al. | To address this issue, we propose a novel visual try-on network, namely Adaptive Content Generating and Preserving Network (ACGPN). | CS.cvpr | 2020-06-08 |
| 483 | ViewAL: Active Learning With Viewpoint Entropy For Semantic Segmentation | YAWAR SIDDIQUI et. al. | We propose ViewAL, a novel active learning strategy for semantic segmentation that exploits viewpoint consistency in multi-view datasets. | CS.cvpr | 2020-06-08 |
| 484 | RandLA-Net: Efficient Semantic Segmentation Of Large-Scale Point Clouds | QINGYONG HU et. al. | In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds. | CS.cvpr | 2020-06-08 |
| 485 | Bidirectional Graph Reasoning Network For Panoptic Segmentation | YANGXIN WU et. al. | We introduce a Bidirectional Graph Reasoning Network (BGRNet), which incorporates graph structure into the conventional panoptic segmentation network to mine the intra-modular and inter-modular relations within and between foreground things and background stuff classes. | CS.cvpr | 2020-06-08 |
| 486 | CRNet: Cross-Reference Networks For Few-Shot Segmentation | WEIDE LIU et. al. | In this paper, we propose a cross-reference network (CRNet) for few-shot segmentation. | CS.cvpr | 2020-06-08 |
| 487 | Temporally Distributed Networks For Fast Video Semantic Segmentation | PING HU et. al. | We present TDNet, a temporally distributed network designed for fast and accurate video semantic segmentation. | CS.cvpr | 2020-06-08 |
| 488 | Enhancing Generic Segmentation With Learned Region Representations | OR ISAACS et. al. | We propose an alternative approach called Deep Generic Segmentation (DGS) and try to follow the path used for semantic segmentation. | CS.cvpr | 2020-06-08 |
| 489 | Local Context Normalization: Revisiting Local Normalization | ANTHONY ORTIZ et. al. | We propose an algorithmic solution to make LCN efficient for arbitrary window sizes, even if every point in the image has a unique window. | CS.cvpr | 2020-06-08 |
| 490 | Strip Pooling: Rethinking Spatial Pooling For Scene Parsing | QIBIN HOU et. al. | In this paper, beyond conventional spatial pooling that usually has a regular shape of NxN, we rethink the formulation of spatial pooling by introducing a new pooling strategy, called strip pooling, which considers a long but narrow kernel, i.e., 1xN or Nx1. | CS.cvpr | 2020-06-08 |
| 491 | Probabilistic Semantic Mapping For Urban Autonomous Driving Applications | DAVID PAZ et. al. | As an attempt to tackle this problem, we propose to fuse image and pre-built point cloud map information to perform automatic and accurate labeling of static landmarks such as roads, sidewalks, crosswalks, and lanes. | CS.arxiv | 2020-06-08 |
| 492 | PuppeteerGAN: Arbitrary Portrait Animation With Semantic-Aware Appearance Transformation | ZHUO CHEN et. al. | In this paper, we devised a novel two-stage framework called PuppeteerGAN for solving these challenges. | CS.cvpr | 2020-06-08 |
| 493 | Panoptic-DeepLab: A Simple, Strong, And Fast Baseline For Bottom-Up Panoptic Segmentation | BOWEN CHENG et. al. | In this work, we introduce Panoptic-DeepLab, a simple, strong, and fast system for panoptic segmentation, aiming to establish a solid baseline for bottom-up methods that can achieve comparable performance of two-stage methods while yielding fast inference speed. | CS.cvpr | 2020-06-08 |
| 494 | CascadePSP: Toward Class-Agnostic And Very High-Resolution Segmentation Via Global And Local Refinement | HO KEI CHENG et. al. | In this paper, we propose a novel approach to address the high-resolution segmentation problem without using any high-resolution training data. | CS.cvpr | 2020-06-08 |
| 495 | Differential Treatment For Stuff And Things: A Simple Unsupervised Domain Adaptation Method For Semantic Segmentation | ZHONGHAO WANG et. al. | We consider the problem of unsupervised domain adaptation for semantic segmentation by easing the domain shift between the source domain (synthetic data) and the target domain (real data) in this work. | CS.cvpr | 2020-06-08 |
| 496 | A Local-to-Global Approach To Multi-Modal Movie Scene Segmentation | ANYI RAO et. al. | Towards this goal, we scale up the scene segmentation task by building a large-scale video dataset MovieScenes, which contains 21K annotated scene segments from 150 movies. We further propose a local-to-global scene segmentation framework, which integrates multi-modal information across three levels, i.e. clip, segment, and movie. | CS.cvpr | 2020-06-08 |
| 497 | Warp To The Future: Joint Forecasting Of Features And Feature Motion | JOSIP SARIC et. al. | We propose to address this issue by complementing F2M forecasting with the classic F2F approach. | CS.cvpr | 2020-06-08 |
| 498 | Learning Fast And Robust Target Models For Video Object Segmentation | ANDREAS ROBINSON et. al. | We propose a novel VOS architecture consisting of two network components. | CS.cvpr | 2020-06-08 |
| 499 | An End-to-End Edge Aggregation Network For Moving Object Segmentation | PRASHANT W. PATIL et. al. | In this paper, the inherent correlation learning-based edge extraction mechanism (EEM) and dense residual block (DRB) are proposed for the discriminative foreground representation. | CS.cvpr | 2020-06-08 |
| 500 | Single-Stage Semantic Segmentation From Image Labels | NIKITA ARASLANOV et. al. | In this work, we first define three desirable properties of a weakly supervised method: local consistency, semantic fidelity, and completeness. Using these properties as guidelines, we then develop a segmentation-based network model and a self-supervised training scheme to train for semantic masks from image-level annotations in a single stage. | CS.cvpr | 2020-06-08 |
| 501 | State-Aware Tracker For Real-Time Video Object Segmentation | XI CHEN et. al. | In this work, we address the task of semi-supervised video object segmentation (VOS) and explore how to make efficient use of video property to tackle the challenge of semi-supervision. | CS.cvpr | 2020-06-08 |
| 502 | Online Knowledge Distillation Via Collaborative Learning | QIUSHAN GUO et. al. | This work presents an efficient yet effective online Knowledge Distillation method via Collaborative Learning, termed KDCL, which is able to consistently improve the generalization ability of deep neural networks (DNNs) that have different learning capacities. | CS.cvpr | 2020-06-08 |
| 503 | Phase Consistent Ecological Domain Adaptation | YANCHAO YANG et. al. | We introduce two criteria to regularize the optimization involved in learning a classifier in a domain where no annotated data are available, leveraging annotated data in a different domain, a problem known as unsupervised domain adaptation. | CS.cvpr | 2020-06-08 |
| 504 | Cross-Domain Semantic Segmentation Via Domain-Invariant Interactive Relation Transfer | FENGMAO LV et. al. | In this paper, we propose a new domain adaptation approach, called Pivot Interaction Transfer (PIT). | CS.cvpr | 2020-06-08 |
| 505 | Agriculture-Vision: A Large Aerial Image Database For Agricultural Pattern Analysis | MANG TIK CHIU et. al. | To encourage research in computer vision for agriculture, we present Agriculture-Vision: a large-scale aerial farmland image dataset for semantic segmentation of agricultural patterns. | CS.cvpr | 2020-06-08 |
| 506 | Severity-Aware Semantic Segmentation With Reinforced Wasserstein Training | XIAOFENG LIU et. al. | To sidestep this, in this work, we propose to incorporate the severity-aware inter-class correlation into our Wasserstein training framework by configuring its ground distance matrix. | CS.cvpr | 2020-06-08 |
| 507 | Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation | DWARIKANATH MAHAPATRA et. al. | We propose improvements over previous GAN-based medical image synthesis methods by jointly encoding the intrinsic relationship of geometry and shape. | CS.cvpr | 2020-06-08 |
| 508 | Stochastic Classifiers For Unsupervised Domain Adaptation | ZHIHE LU et. al. | In this paper, we introduce a novel method called STochastic clAssifieRs (STAR) for addressing this problem. | CS.cvpr | 2020-06-08 |
| 509 | SpSequenceNet: Semantic Segmentation Network On 4D Point Clouds | HANYU SHI et. al. | In this paper, we propose SpSequenceNet to address this problem. | CS.cvpr | 2020-06-08 |
| 510 | PointRend: Image Segmentation As Rendering | ALEXANDER KIRILLOV et. al. | We present a new method for efficient high-quality image segmentation of objects and scenes. | CS.cvpr | 2020-06-08 |
| 511 | DualConvMesh-Net: Joint Geodesic And Euclidean Convolutions On 3D Meshes | JONAS SCHULT et. al. | We propose DualConvMesh-Nets (DCM-Net) a family of deep hierarchical convolutional networks over 3D geometric data that combines two types of convolutions. | CS.cvpr | 2020-06-08 |
| 512 | Exemplar Normalization For Learning Deep Representation | RUIMAO ZHANG et. al. | This work investigates a novel dynamic learning-to-normalize (L2N) problem by proposing Exemplar Normalization (EN), which is able to learn different normalization methods for different convolutional layers and image samples of a deep network. | CS.cvpr | 2020-06-08 |
| 513 | Can We Learn Heuristics For Graphical Model Inference Using Reinforcement Learning? | SAFA MESSAOUD et. al. | In this paper, we show that we can learn program heuristics, i.e., policies, for solving inference in higher order CRFs for the task of semantic segmentation, using reinforcement learning. | CS.cvpr | 2020-06-08 |
| 514 | Light-weight Calibrator: A Separable Component For Unsupervised Domain Adaptation | SHAOKAI YE et. al. | In this work, instead of training a classifier to adapt to the target domain, we use a separable component called data calibrator to help the fixed source classifier recover discrimination power in the target domain, while preserving the source domain’s performance. | CS.cvpr | 2020-06-08 |
| 515 | FSS-1000: A 1000-Class Dataset For Few-Shot Segmentation | XIANG LI et. al. | In this paper, we are interested in few-shot object segmentation where the number of annotated training examples are limited to 5 only. To evaluate and validate the performance of our approach, we have built a few-shot segmentation dataset, FSS-1000, which consists of 1000 object classes with pixelwise annotation of ground-truth segmentation. | CS.cvpr | 2020-06-08 |
| 516 | Cars Can’t Fly Up In The Sky: Improving Urban-Scene Segmentation Via Height-Driven Attention Networks | SUNGHA CHOI et. al. | This paper exploits the intrinsic features of urban-scene images and proposes a general add-on module, called height-driven attention networks (HANet), for improving semantic segmentation for urban-scene images. | CS.cvpr | 2020-06-08 |
| 517 | TESA: Tensor Element Self-Attention Via Matricization | FRANCESCA BABILONI et. al. | In this paper, we introduce a new method, called Tensor Element Self-Attention (TESA) that generalizes such work to capture interdependencies along all dimensions of the tensor using matricization. | CS.cvpr | 2020-06-08 |
| 518 | Learning Integral Objects With Intra-Class Discriminator For Weakly-Supervised Semantic Segmentation | JUNSONG FAN et. al. | In this paper, we argue that the critical factor preventing to obtain the full object mask is the classification boundary mismatch problem in applying the CAM to WSSS. | CS.cvpr | 2020-06-08 |
| 519 | Are We Hungry For 3D LiDAR Data For Semantic Segmentation? | BIAO GAO et. al. | This survey aims to explore whether and how we are hungry for 3D LiDAR data for semantic segmentation. | CS.arxiv | 2020-06-07 |
| 520 | Learning Pose Variations Within Shape Population By Constrained Mixtures Of Factor Analyzers | XILU WANG | This paper formulates the pose learning problem as mixtures of factor analyzers. | CS.arxiv | 2020-06-07 |
| 521 | Instance Segmentation Of Buildings Using Keypoints | QINGYU LI et. al. | In this paper, we propose a novel instance segmentation network for building segmentation in high-resolution remote sensing images. | CS.arxiv | 2020-06-06 |
| 522 | Visual Transformers: Token-based Image Representation And Processing For Computer Vision | BICHEN WU et. al. | In this work, we challenge this paradigm: we instead (a) represent images as a set of visual tokens and (b) apply visual transformers to find relationships between visual semantic concepts. | CS.arxiv | 2020-06-05 |
| 523 | RIT-Eyes: Rendering Of Near-eye Images For Eye-tracking Applications | NITINRAJ NAIR et. al. | In this work, we introduce a synthetic eye image generation platform that improves upon previous work by adding features such as an active deformable iris, an aspherical cornea, retinal retro-reflection, gaze-coordinated eye-lid deformations, and blinks. | CS.arxiv | 2020-06-05 |
| 524 | Equivariant Maps For Hierarchical Structures | RENHAO WANG et. al. | Observing that the transformation group for a nested structure corresponds to the “wreath product” of the symmetry groups of the building blocks, we show how to obtain the equivariant map for hierarchical data-structures using an intuitive combination of the equivariant maps for the individual blocks. | CS.arxiv | 2020-06-05 |
| 525 | Segmentation Of Surgical Instruments For Minimally-Invasive Robot-Assisted Procedures Using Generative Deep Neural Networks | IÑIGO AZQUETA-GAVALDON et. al. | This work proves that semantic segmentation on minimally invasive surgical instruments can be improved by using training data that has been augmented through domain adaptation. | CS.arxiv | 2020-06-05 |
| 526 | A Soft Humanoid Hand With In-Finger Visual Perception | FELIX HUNDHAUSEN et. al. | We present a novel underactued humanoid five finger soft hand, the KIT \softhand, which is equipped with cameras in the fingertips and integrates a high performance embedded system for visual processing and control. | CS.arxiv | 2020-06-05 |
| 527 | Dilated Convolutions With Lateral Inhibitions For Semantic Image Segmentation | YUJIANG WANG et. al. | Inspired by the Lateral Inhibition (LI) mechanisms in human visual systems, we propose the dilated convolution with lateral inhibitions (LI-Convs) to overcome these limitations. | CS.arxiv | 2020-06-05 |
| 528 | LRNNet: A Light-Weighted Network With Efficient Reduced Non-Local Operation For Real-Time Semantic Segmentation | WEIHAO JIANG et. al. | This paper introduces a light-weighted network with an efficient reduced non-local module (LRNNet) for efficient and realtime semantic segmentation. | CS.arxiv | 2020-06-04 |
| 529 | Boundary-assisted Region Proposal Networks For Nucleus Segmentation | SHENGCONG CHEN et. al. | Accordingly, in this paper, we devise a Boundary-assisted Region Proposal Network (BRP-Net) that achieves robust instance-level nucleus segmentation. | CS.arxiv | 2020-06-04 |
| 530 | Exploiting The Transferability Of Deep Learning Systems Across Multi-modal Retinal Scans For Extracting Retinopathy Lesions | TAIMUR HASSAN et. al. | A total of 363 fundus and 173,915 OCT scans from seven publicly available datasets were used in this research (from which 297 fundus and 59,593 OCT scans were used for testing purposes). | CS.arxiv | 2020-06-04 |
| 531 | MSDU-net: A Multi-Scale Dilated U-net For Blur Detection | FAN YANG et. al. | In this work, we regard blur detection as an image segmentation problem. | CS.arxiv | 2020-06-04 |
| 532 | Multi-scale Cloud Detection In Remote Sensing Images Using A Dual Convolutional Neural Network | MARKKU LUOTAMO et. al. | To support a wider scale of spatial features while simultaneously reducing computational requirements for large satellite images, we propose an architecture of two cascaded CNN model components successively processing undersampled and full resolution images. | CS.arxiv | 2020-06-01 |
| 533 | Critical Assessment Of Transfer Learning For Medical Image Segmentation With Fully Convolutional Neural Networks | DAVOOD KARIMI et. al. | Transfer learning is widely used for training machine learning models. | CS.arxiv | 2020-05-30 |
| 534 | WaveSNet: Wavelet Integrated Deep Networks For Image Segmentation | QIUFU LI et. al. | In this paper, we propose to apply Discrete Wavelet Transform (DWT) to extract the data details during feature map down-sampling, and adopt Inverse DWT (IDWT) with the extracted details during the up-sampling to recover the details. | CS.arxiv | 2020-05-29 |
| 535 | Reducing DNN Labelling Cost Using Surprise Adequacy: An Industrial Case Study For Autonomous Driving | JINHAN KIM et. al. | This paper shows how development of DNN based object segmentation can be improved by exploiting the correlation between Surprise Adequacy (SA) and model performance. | CS.arxiv | 2020-05-29 |
| 536 | NuClick: A Deep Learning Framework For Interactive Segmentation Of Microscopy Images | NAVID ALEMI KOOHBANANI et. al. | For multicellular structures such as glands, we propose a novel approach to provide the NuClick with a squiggle as a guiding signal, enabling it to segment the glandular boundaries. As exemplar outputs of our framework, we are releasing two datasets: 1) a dataset of lymphocyte annotations within IHC images, and 2) a dataset of segmented WBCs in blood smear images. | CS.arxiv | 2020-05-29 |
| 537 | Automated Measurements Of Key Morphological Features Of Human Embryos For IVF | BRIAN D. LEAHY et. al. | Our approach greatly speeds up the measurement of quantitative, biologically relevant features that may aid in embryo selection. | CS.arxiv | 2020-05-29 |
| 538 | Overview: Computer Vision And Machine Learning For Microstructural Characterization And Analysis | ELIZABETH A. HOLM et. al. | These tools enable new approaches to microstructural analysis, including the development of new, rich visual metrics and the discovery of processing-microstructure-property relationships. | CS.arxiv | 2020-05-28 |
| 539 | Traditional Method Inspired Deep Neural Network For Edge Detection | JAN KRISTANTO WIBISONO et. al. | Therefore, we propose a traditional method inspired framework to produce good edges with minimal complexity. | CS.arxiv | 2020-05-28 |
| 540 | Accelerating Neural Network Inference By Overflow Aware Quantization | HONGWEI XIE et. al. | To address this problem, we propose an overflow aware quantization method by designing trainable adaptive fixed-point representation, to optimize the number of bits for each input tensor while prohibiting numeric overflow during the computation. | CS.arxiv | 2020-05-27 |
| 541 | GSTO: Gated Scale-Transfer Operation For Multi-Scale Feature Learning In Pixel Labeling | ZHUOYING WANG et. al. | In this work, we find that these operations lead to scale-confused features and suboptimal performance because they are spatial-invariant and directly transit all feature information cross scales without spatial selection. | CS.arxiv | 2020-05-27 |
| 542 | Learning To Segment From Misaligned And Partial Labels | SIMONE FOBI et. al. | In this paper, we present a novel and generalizable two-stage framework that enables improved pixel-wise image segmentation given misaligned and missing annotations. | CS.arxiv | 2020-05-27 |
| 543 | Multi-task Deep Learning For Image Segmentation Using Recursive Approximation Tasks | RIHUAN KE et. al. | In this work, we develop a multi-task learning method to relax this constraint. | CS.arxiv | 2020-05-26 |
| 544 | ALBA : Reinforcement Learning For Video Object Segmentation | SHREYANK N GOWDA et. al. | We propose a network architecture for tractably performing proposal selection and joint grouping. | CS.arxiv | 2020-05-26 |
| 545 | Egocentric Human Segmentation For Mixed Reality | ANDRIJA GAJIC et. al. | The objective of this work is to segment human body parts from egocentric video using semantic segmentation networks. Our contribution is two-fold: i) we create a semi-synthetic dataset composed of more than 15, 000 realistic images and associated pixel-wise labels of egocentric human body parts, such as arms or legs including different demographic factors; ii) building upon the ThunderNet architecture, we implement a deep learning semantic segmentation algorithm that is able to perform beyond real-time requirements (16 ms for 720 x 720 images). | CS.arxiv | 2020-05-25 |
| 546 | Visual Localization Using Semantic Segmentation And Depth Prediction | HUANHUAN FAN et. al. | In this paper, we propose a monocular visual localization pipeline leveraging semantic and depth cues. | CS.arxiv | 2020-05-25 |
| 547 | Bi-direction Context Propagation Network For Real-time Semantic Segmentation | SHIJIE HAO et. al. | To address this problem, we propose the Bi-direction Context Propagation Network (BCPNet) by leveraging both spatial and context information. | CS.arxiv | 2020-05-22 |
| 548 | Gleason Grading Of Histology Prostate Images Through Semantic Segmentation Via Residual U-Net | AMARTYA KALAPAHAR et. al. | Gleason Grading Of Histology Prostate Images Through Semantic Segmentation Via Residual U-Net | CS.arxiv | 2020-05-22 |
| 549 | Panoptic Instance Segmentation On Pigs | JOHANNES BRÜNGER et. al. | Therefore this work follows the relatively new definition of a panoptic segmentation and aims at the pixel accurate segmentation of the individual pigs. | CS.arxiv | 2020-05-21 |
| 550 | Manifold Alignment For Semantically Aligned Style Transfer | JING HUO et. al. | In this paper, we make a different assumption that local semantically aligned (or similar) regions between the content and style images should share similar style patterns. | CS.arxiv | 2020-05-21 |
| 551 | Hierarchical Multi-Scale Attention For Semantic Segmentation | ANDREW TAO et. al. | In this work, we present an attention-based approach to combining multi-scale predictions. | CS.arxiv | 2020-05-21 |
| 552 | Unsupervised Domain Adaptation In Semantic Segmentation: A Review | MARCO TOLDO et. al. | The aim of this paper is to give an overview of the recent advancements in the Unsupervised Domain Adaptation (UDA) of deep networks for semantic segmentation. | CS.arxiv | 2020-05-21 |
| 553 | Deep Learning-Based Automated Image Segmentation For Concrete Petrographic Analysis | YU SONG et. al. | In this study, we investigated the feasibility of using CNN to conduct concrete segmentation without the use of color treatment. | CS.arxiv | 2020-05-20 |
| 554 | Label Efficient Visual Abstractions For Autonomous Driving | ASEEM BEHL et. al. | In this work, we seek to quantify the impact of reducing segmentation annotation costs on learned behavior cloning agents. | CS.arxiv | 2020-05-20 |
| 555 | Deep Learning For LiDAR Point Clouds In Autonomous Driving: A Review | YING LI et. al. | In this paper, we provide a systematic review of existing compelling deep learning architectures applied in LiDAR point clouds, detailing for specific tasks in autonomous driving such as segmentation, detection, and classification. | CS.arxiv | 2020-05-19 |
| 556 | Multi-modal Sensor Fusion-Based Deep Neural Network For End-to-end Autonomous Driving With Scene Understanding | ZHIYU HUANG et. al. | This study aims to improve the performance and generalization capability of end-to-end autonomous driving with scene understanding leveraging deep learning and multimodal sensor fusion techniques. | CS.arxiv | 2020-05-19 |
| 557 | Decoder Modulation For Indoor Depth Completion | DMITRY SENUSHKIN et. al. | The main contributions of our work are two-fold. | CS.arxiv | 2020-05-18 |
| 558 | Guided Interactive Image Segmentation Using Machine Learning And Color Based Data Set Clustering | ADRIAN FRIEBEL et. al. | We present a novel approach that combines machine learning based interactive image segmentation with a two-stage clustering method for identification of similarly colored images enabling efficient batch image segmentation through guided reuse of interactively trained classifiers. | CS.arxiv | 2020-05-15 |
| 559 | Convex Shape Prior For Deep Neural Convolution Network Based Eye Fundus Images Segmentation | JUN LIU et. al. | In this work, we propose a technique which can be easily integrated into the commonly used DCNNs for image segmentation and guarantee that outputs are convex shapes. | CS.arxiv | 2020-05-15 |
| 560 | Detection And Retrieval Of Out-of-Distribution Objects In Semantic Segmentation | PHILIPP OBERDIEK et. al. | We present a novel pipeline for semantic segmenation that detects out-of-distribution (OOD) segments by means of the deep neural network’s prediction and performs image retrieval after feature extraction and dimensionality reduction on image patches. | CS.arxiv | 2020-05-14 |
| 561 | SUPER: A Novel Lane Detection System | PINGPING LU et. al. | In this paper, we propose a real-time lane detection system, called Scene Understanding Physics-Enhanced Real-time (SUPER) algorithm. | CS.arxiv | 2020-05-14 |
| 562 | Taskology: Utilizing Task Relations At Scale | YAO LU et. al. | To this end, we aim to establish and explore a novel approach for the collective training of computer vision tasks. | CS.arxiv | 2020-05-14 |
| 563 | SRDA-Net: Super-Resolution Domain Adaptation Networks For Semantic Segmentation | ZHENJIE TANG et. al. | In this work, we design a novel end-to-end semantic segmentation network, Super-Resolution Domain Adaptation Network (SRDA-Net), which could simultaneously complete super-resolution and domain adaptation. | CS.arxiv | 2020-05-13 |
| 564 | Exploiting Multi-Layer Grid Maps For Surround-View Semantic Segmentation Of Sparse LiDAR Data | FRANK BIEDER et. al. | In this paper, we consider the transformation of laser range measurements into a top-view grid map representation to approach the task of LiDAR-only semantic segmentation. | CS.arxiv | 2020-05-13 |
| 565 | Probabilistic Semantic Segmentation Refinement By Monte Carlo Region Growing | PHILIPE A. DIAS et. al. | We introduce a fully unsupervised post-processing algorithm that exploits Monte Carlo sampling and pixel similarities to propagate high-confidence pixel labels into regions of low-confidence classification. | CS.arxiv | 2020-05-12 |
| 566 | Class-Incremental Learning For Semantic Segmentation Re-Using Neither Old Data Nor Old Labels | MARVIN KLINGNER et. al. | We evaluate our method on the Cityscapes dataset, where we exceed the mIoU performance of all baselines by 3.5% absolute reaching a result, which is only 2.2% absolute below the upper performance limit of single-stage training, relying on all data and labels simultaneously. | CS.arxiv | 2020-05-12 |
| 567 | Stillleben: Realistic Scene Synthesis For Deep Learning In Robotics | MAX SCHWARZ et. al. | We describe a synthesis pipeline capable of producing training data for cluttered scene perception tasks such as semantic segmentation, object detection, and correspondence or pose estimation. | CS.arxiv | 2020-05-12 |
| 568 | ECG-DelNet: Delineation Of Ambulatory Electrocardiograms With Mixed Quality Labeling Using Neural Networks | GUILLERMO JIMENEZ-PEREZ et. al. | We demonstrate DL can be successfully applied to low interpretative tasks by embedding ECG detection and delineation onto a segmentation framework. | CS.arxiv | 2020-05-11 |
| 569 | A Weighted Difference Of Anisotropic And Isotropic Total Variation For Relaxed Mumford-Shah Color And Multiphase Image Segmentation | KEVIN BUI et. al. | To deal with the weighted anisotropic-isotropic TV, we apply the difference-of-convex algorithm (DCA), where the subproblems can be minimized by the primal-dual hybrid gradient method (PDHG). | CS.arxiv | 2020-05-09 |
| 570 | OpenEDS2020: Open Eyes Dataset | CRISTINA PALMERO et. al. | We present the second edition of OpenEDS dataset, OpenEDS2020, a novel dataset of eye-image sequences captured at a frame rate of 100 Hz under controlled illumination, using a virtual-reality head-mounted display mounted with two synchronized eye-facing cameras. | CS.arxiv | 2020-05-08 |
| 571 | Source-Relaxed Domain Adaptation For Image Segmentation | MATHILDE BATESON et. al. | We propose a novel formulation for adapting segmentation networks, which relaxes such a constraint. | CS.arxiv | 2020-05-07 |
| 572 | Manipulated Face Detector: Joint Spatial And Frequency Domain Attention Network | ZEHAO CHEN et. al. | In this paper, we propose a novel manipulated face detector, which is based on spatial and frequency domain combination and attention mechanism. | CS.arxiv | 2020-05-06 |
| 573 | LandCover.ai: Dataset For Automatic Mapping Of Buildings, Woodlands And Water From Aerial Imagery | ADRIAN BOGUSZEWSKI et. al. | Here we introduce LandCover.ai (Land Cover from Aerial Imagery) dataset for semantic segmentation. | CS.arxiv | 2020-05-05 |
| 574 | Illumination-Invariant Image From 4-Channel Images: The Effect Of Near-Infrared Data In Shadow Removal | SOROUR MOHAJERANI et. al. | In this study, we examine the quality of illumination-invariant images generated from red, green, blue, and near-infrared (RGBN) data. | CS.arxiv | 2020-05-04 |
| 575 | How To Train Your Dragon: Tamed Warping Network For Semantic Video Segmentation | JUNYI FENG et. al. | In this paper, we propose to introduce a simple and effective correction stage right after the warping stage to form a framework named Tamed Warping Network (TWNet), aiming to improve the accuracy and robustness of warping-based models. | CS.arxiv | 2020-05-04 |
| 576 | DroTrack: High-speed Drone-based Object Tracking Under Uncertainty | ALI HAMDI et. al. | We present DroTrack, a high-speed visual single-object tracking framework for drone-captured video sequences. | CS.arxiv | 2020-05-02 |
| 577 | Deeply Cascaded U-Net For Multi-Task Image Processing | ILJA GUBINS et. al. | In this paper, we propose a novel multi-task neural network architecture designed for combining sequential image processing tasks. | CS.arxiv | 2020-05-01 |
| 578 | Computing The Testing Error Without A Testing Set | CIPRIAN CORNEANU et. al. | Here, we derive an algorithm to estimate the performance gap between training and testing that does not require any testing dataset. | CS.arxiv | 2020-05-01 |
| 579 | ACCL: Adversarial Constrained-CNN Loss For Weakly Supervised Medical Image Segmentation | PENGYI ZHANG et. al. | We propose adversarial constrained-CNN loss, a new paradigm of constrained-CNN loss methods, for weakly supervised medical image segmentation. | CS.arxiv | 2020-05-01 |
| 580 | Improving Semantic Segmentation Via Self-Training | YI ZHU et. al. | In this paper, we show that we can obtain state-of-the-art results using a semi-supervised approach, specifically a self-training paradigm. | CS.arxiv | 2020-04-30 |
| 581 | SS3D: Single Shot 3D Object Detector | ANIKET LIMAYE et. al. | In this paper we present Single Shot 3D Object Detection (SS3D) – a single stage 3D object detection algorithm which combines straight forward, statistically computed input representation and a Single Shot Detector (based on PointPillars). | CS.arxiv | 2020-04-30 |
| 582 | Feedback U-net For Cell Image Segmentation | EISUKE SHIBUYA et. al. | Therefore, in this paper, we propose Feedback U-Net using Convolutional LSTM which is the segmentation method using Convolutional LSTM and feedback process. | CS.arxiv | 2020-04-30 |
| 583 | Polygonal Building Segmentation By Frame Field Learning | NICOLAS GIRARD et. al. | We propose adding a frame field output to a deep image segmentation model for extracting buildings from remote sensing images. | CS.arxiv | 2020-04-30 |
| 584 | Importance Driven Continual Learning For Segmentation Across Domains | SINAN ÖZGÜR ÖZGÜN et. al. | In this work, we propose a Continual Learning approach for brain segmentation, where a single network is consecutively trained on samples from different domains. | CS.arxiv | 2020-04-30 |
| 585 | Salient Object Detection Combining A Self-attention Module And A Feature Pyramid Network | GUANGYU REN et. al. | To this end, in order to overcome this limitation, we propose a novel pyramid self-attention module (PSAM) and the adoption of an independent feature-complementing strategy. | CS.arxiv | 2020-04-29 |
| 586 | Counting Of Grapevine Berries In Images Via Semantic Segmentation Using Convolutional Neural Networks | LAURA ZABAWA et. al. | In this paper we present an objective framework based on automatic image analysis which works on two different training systems. | CS.arxiv | 2020-04-29 |
| 587 | Distance Guided Channel Weighting For Semantic Segmentation | LANYUN ZHU et. al. | In this paper, we address above issue by introducing the Distance Guided Channel Weighting (DGCW) Module. | CS.arxiv | 2020-04-27 |
| 588 | GIMP-ML: Python Plugins For Using Computer Vision Models In GIMP | KRITIK SOMAN | This paper introduces GIMP-ML v1.1, a set of Python plugins for the widely popular GNU Image Manipulation Program (GIMP). | CS.arxiv | 2020-04-27 |
| 589 | Compact Retail Shelf Segmentation For Mobile Deployment | PRATYUSH KUMAR et. al. | In this paper, we work on one such common problem in the retail industries – Shelf segmentation. | CS.arxiv | 2020-04-27 |
| 590 | Unsupervised Domain Adaptation With Multiple Domain Discriminators And Adaptive Self-Training | TEO SPADOTTO et. al. | In this paper, we consider the semantic segmentation of urban scenes and we propose an approach to adapt a deep neural network trained on synthetic data to real scenes addressing the domain shift between the two different data distributions. | CS.arxiv | 2020-04-27 |
| 591 | Weakly Supervised Semantic Segmentation In 3D Graph-Structured Point Clouds Of Wild Scenes | HAIYAN WANG et. al. | To alleviate this issue, we propose a novel deep graph convolutional network-based framework for large-scale semantic scene segmentation in point clouds with sole 2D supervision. | CS.arxiv | 2020-04-26 |
| 592 | Arnet: Attention-Based Refinement Network For Few-Shot Semantic Segmentation | R. LI et. al. | In this paper, we propose an Attention-based Refinement Network (ARNet) for few-shot semantic segmentation, which consists of three branches: the guidance branch, the segmentation branch and the refinement branch. | CS.icassp | 2020-04-26 |
| 593 | Weakly Supervised Semantic Segmentation For Remote Sensing Hyperspectral Imaging | E. MOLINER et. al. | This paper studies the problem of training a semantic segmentation neural network with weak annotations, in order to be applied in aerial vegetation images from Teide National Park. | CS.icassp | 2020-04-26 |
| 594 | Unsupervised Domain Adaptation For Semantic Segmentation With Symmetric Adaptation Consistency | Z. LI et. al. | In this paper, we utilize adversarial learning and semi-supervised learning simultaneously to solve the task of unsupervised domain adaptation in semantic segmentation. | CS.icassp | 2020-04-26 |
| 595 | Signal Clustering With Class-Independent Segmentation | S. GASPERINI et. al. | In this paper we propose a Deep Learning-based clustering method, which encodes concurrent signals into images, and, for the first time, tackles clustering with image segmentation. | CS.icassp | 2020-04-26 |
| 596 | Acu-Net: A 3D Attention Context U-Net For Multiple Sclerosis Lesion Segmentation | C. HU et. al. | To solve the problem, 3D attention context U-Net (ACU-Net) is proposed for MS lesion segmentation in this paper. | CS.icassp | 2020-04-26 |
| 597 | UNet 3+: A Full-Scale Connected UNet For Medical Image Segmentation | H. HUANG ET AL. | In this paper, we propose a novel UNet 3+, which takes advantage of full-scale skip connections and deep supervisions. | CS.icassp | 2020-04-26 |
| 598 | Adaptive Elastic Loss Based On Progressive Inter-Class Association For Cervical Histology Image Segmentation | Z. MENG et. al. | In this paper, an end-to-end deep segmentation network for complex cervical histology images is proposed, and a benchmark evaluation is contributed. | CS.icassp | 2020-04-26 |
| 599 | Human-Machine Collaboration For Medical Image Segmentation | M. RAVANBAKHSH ET AL. | In this paper, we propose a method based on conditional Generative Adversarial Network (cGAN) to address segmentation in semi-supervised setup and in a human-in-the-loop fashion. | CS.icassp | 2020-04-26 |
| 600 | A Dense U-Net With Cross-Layer Intersection For Detection And Localization Of Image Forgery | R. ZHANG AND J. NI | In this paper, we apply cross-layer intersection mechanism to dense u-net for image forgery detection and localization. | CS.icassp | 2020-04-26 |
| 601 | A Multi-Scaled Receptive Field Learning Approach For Medical Image Segmentation | P. GUO et. al. | To solve this problem, this paper integrates an atrous spatial pyramid pooling (ASPP) module in the contracting path of attention U-Net. | CS.icassp | 2020-04-26 |
| 602 | Hybrid Active Contour Driven By Double-Weighted Signed Pressure Force For Image Segmentation | X. FU et. al. | In this paper, we proposed a novel hybrid active contour driven by double-weighted signed pressure force method for image segmentation. | CS.icassp | 2020-04-26 |
| 603 | A Deep Learning Approach To Object Affordance Segmentation | S. THERMOS et. al. | In this paper, we propose a novel approach that exploits the spatio-temporal nature of human-object interaction for affordance segmentation. | CS.icassp | 2020-04-26 |
| 604 | Learning Local Structure Of Representative Points For Point Cloud Classification And Semantic Segmentation | X. LI et. al. | To solve this problem, we propose a learning-based block, named Representative Points Block (RPB), to select the most representative points of an irregular point cloud according to the task. | CS.icassp | 2020-04-26 |
| 605 | Drift Detection And Correction Post-Tracking | T. GHONIEMY AND M. A. AMER | This paper proposes a method that first detects, at each frame, if a tracker tends to drift by analyzing saliency features of the output BB of a tracker, and then applies automatic seeded object segmentation on the BB to correct the drift once detected. | CS.icassp | 2020-04-26 |
| 606 | A Multi-Dilation And Multi-Resolution Fully Convolutional Network For Singing Melody Extraction | P. GAO et. al. | In this paper, we propose a neural network, which includes spectro-temporal multi-resolution decomposition of the log-spectrogram of the sound and a semantic segmentation model to respectively address the bottom-up and top-down processing of hearing, for singing melody extraction. | CS.icassp | 2020-04-26 |
| 607 | A Probabilistic Scheme For Representation Learning With Radial Transform Images | H. SALEHINEJAD AND S. VALAEE | In this paper, a probabilistic framework to analyze radial transform is presented. | CS.icassp | 2020-04-26 |
| 608 |