Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

Abstract

Most state-of-the-art techniques for multi-class image segmentation and labeling use conditional random fields defined over pixels or image regions. While region-level models often feature dense pairwise connectivity, pixel-level models are considerably larger and have only permitted sparse graph structures. In this paper, we consider fully connected CRF models defined on the complete set of pixels in an image. The resulting graphs have billions of edges, making traditional inference algorithms impractical. Our main contribution is a highly efficient approximate inference algorithm for fully connected CRF models in which the pairwise edge potentials are defined by a linear combination of Gaussian kernels. Our experiments demonstrate that dense connectivity at the pixel level substantially improves segmentation and labeling accuracy.

NIPS 2011

Cited by in corpus (617)

• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Conditional Random Fields as Recurrent Neural Networks
• UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery
• A Review on Deep Learning Techniques Applied to Semantic Segmentation
• A deep learning model integrating FCNNs and CRFs for brain tumor segmentation
• Deeply supervised salient object detection with short connections
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields
• Learning Deconvolution Network for Semantic Segmentation
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• Algorithms for Semantic Segmentation of Multispectral Remote Sensing Imagery using Deep Learning
• Deep Label Distribution Learning with Label Ambiguity
• DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation
• Visual Saliency Detection Based on Multiscale Deep CNN Features
• Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review
• DeepNAT: Deep Convolutional Neural Network for Segmenting Neuroanatomy
• Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
• A Survey on Deep Learning Techniques for Stereo-based Depth Estimation
• Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
• A Comprehensive Survey of Scene Graphs: Generation and Application
• Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
• Constrained-CNN losses for weakly supervised segmentation
• Deep Gradient Learning for Efficient Camouflaged Object Detection
• A Topological Loss Function for Deep-Learning based Image Segmentation using Persistent Homology
• Fully Connected Deep Structured Networks
• Direction-aware Spatial Context Features for Shadow Detection
• Direction-aware Spatial Context Features for Shadow Detection and Removal
• A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images
• Global Guidance Network for Breast Lesion Segmentation in Ultrasound Images
• Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects
• Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network
• One-pass Multi-task Networks with Cross-task Guided Attention for Brain Tumor Segmentation
• CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection
• W-Net: A Deep Model for Fully Unsupervised Image Segmentation
• InversionNet: A Real-Time and Accurate Full Waveform Inversion with CNNs and continuous CRFs
• PseudoSeg: Designing Pseudo Labels for Semantic Segmentation
• Road Segmentation in SAR Satellite Images with Deep Fully-Convolutional Neural Networks
• Deep Image Translation with an Affinity-Based Change Prior for Unsupervised Multimodal Change Detection
• Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation
• Automatic Liver and Tumor Segmentation of CT and MRI Volumes using Cascaded Fully Convolutional Neural Networks
• Gland Instance Segmentation Using Deep Multichannel Neural Networks
• Semantic Image Segmentation via Deep Parsing Network
• Bifurcated backbone strategy for RGB-D salient object detection
• Generative Adversarial Networks and Conditional Random Fields for Hyperspectral Image Classification
• Automatic Brain Tumor Segmentation using Convolutional Neural Networks with Test-Time Augmentation
• From Google Maps to a Fine-Grained Catalog of Street trees
• Bridging Category-level and Instance-level Semantic Image Segmentation
• Mumford-Shah Loss Functional for Image Segmentation with Deep Learning
• Multispecies fruit flower detection using a refined semantic segmentation network
• Playing for Data: Ground Truth from Computer Games
• Non-local Neural Networks
• Unsupervised Image Regression for Heterogeneous Change Detection
• Re-thinking Co-Salient Object Detection
• CNN-based Segmentation of Medical Imaging Data
• CNN-based Density Estimation and Crowd Counting: A Survey
• Deformable Kernel Networks for Joint Image Filtering
• Progressively Normalized Self-Attention Network for Video Polyp Segmentation
• CAGNet: Content-Aware Guidance for Salient Object Detection
• Deep Contrast Learning for Salient Object Detection
• Robotic Vision for Human-Robot Interaction and Collaboration: A Survey and Systematic Review
• Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
• Buildings Detection in VHR SAR Images Using Fully Convolution Neural Networks
• RPC: A Large-Scale Retail Product Checkout Dataset
• Graph Attention Layer Evolves Semantic Segmentation for Road Pothole Detection: A Benchmark and Algorithms
• Semantic Segmentation of Remote Sensing Images with Sparse Annotations
• Puzzle-CAM: Improved localization via matching partial and full features
• PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloud
• Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
• CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation
• Video Salient Object Detection Using Spatiotemporal Deep Features
• Facial Action Unit Detection Using Attention and Relation Learning
• A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains
• TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentation
• PixelNet: Representation of the pixels, by the pixels, and for the pixels
• Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation
• Face Clustering: Representation and Pairwise Constraints
• DSAL: Deeply Supervised Active Learning from Strong and Weak Labelers for Biomedical Image Segmentation
• Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network
• Faster Training of Mask R-CNN by Focusing on Instance Boundaries
• Efficient piecewise training of deep structured models for semantic segmentation
• Automatic Liver Lesion Detection using Cascaded Deep Residual Networks
• Semi-Supervised Segmentation of Radiation-Induced Pulmonary Fibrosis from Lung CT Scans with Multi-Scale Guided Dense Attention
• CGNet: A Light-weight Context Guided Network for Semantic Segmentation
• Monocular Camera Based Fruit Counting and Mapping with Semantic Data Association
• LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation
• Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
• SAC-Net: Spatial Attenuation Context for Salient Object Detection
• Cancer Metastasis Detection With Neural Conditional Random Field
• SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation
• A Multi-Level Approach to Waste Object Segmentation
• Understanding Urban Dynamics via Context-aware Tensor Factorization with Neighboring Regularization
• Tell Me Where to Look: Guided Attention Inference Network
• Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation
• PhotoShape: Photorealistic Materials for Large-Scale Shape Collections
• Learning Video Object Segmentation from Static Images
• Causal Intervention for Weakly-Supervised Semantic Segmentation
• Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentation
• Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
• PhenoBench -- A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural Domain
• The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
• Detecting Visual Relationships with Deep Relational Networks
• Unsupervised Multi-modal Style Transfer for Cardiac MR Segmentation
• Recurrent Multiresolution Convolutional Networks for VHR Image Classification
• ImageSpirit: Verbal Guided Image Parsing
• RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
• Improving Fast Segmentation With Teacher-student Learning
• Reverse Attention for Salient Object Detection
• 2017 Robotic Instrument Segmentation Challenge
• Evidential fully convolutional network for semantic segmentation
• PixelNet: Towards a General Pixel-level Architecture
• Salient Objects in Clutter
• Gated CRF Loss for Weakly Supervised Semantic Image Segmentation
• Normalized Cut Loss for Weakly-supervised CNN Segmentation
• Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation
• APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation
• segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection
• WeGleNet: A Weakly-Supervised Convolutional Neural Network for the Semantic Segmentation of Gleason Grades in Prostate Histology Images
• Progressive Glass Segmentation
• Random Forest with Learned Representations for Semantic Segmentation
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• AMNet: Deep Atrous Multiscale Stereo Disparity Estimation Networks
• Prior Guided Feature Enrichment Network for Few-Shot Segmentation
• Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation
• Looking at Outfit to Parse Clothing
• Dual Convolutional LSTM Network for Referring Image Segmentation
• A fully end-to-end deep learning approach for real-time simultaneous 3D reconstruction and material recognition
• Cross-Modal Self-Attention Network for Referring Image Segmentation
• Learning Video Object Segmentation with Visual Memory
• Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach
• CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning
• Multi-Granularity Denoising and Bidirectional Alignment for Weakly Supervised Semantic Segmentation
• Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networks
• SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks
• Deep Learning Convolutional Networks for Multiphoton Microscopy Vasculature Segmentation
• Addressing Overfitting on Pointcloud Classification using Atrous XCRF
• Adaptive Patch Contrast for Weakly Supervised Semantic Segmentation
• Learning to Exploit the Prior Network Knowledge for Weakly-Supervised Semantic Segmentation
• DFNet: Discriminative feature extraction and integration network for salient object detection
• Adversarial Deep Structural Networks for Mammographic Mass Segmentation
• Deep Multi-Branch Aggregation Network for Real-Time Semantic Segmentation in Street Scenes
• Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
• Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation
• Video Object Segmentation and Tracking: A Survey
• Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation
• Multi-Modal Obstacle Detection in Unstructured Environments with Conditional Random Fields
• Deep Learning for Semantic Part Segmentation with High-Level Guidance
• Guided Upsampling Network for Real-Time Semantic Segmentation
• Tangent Convolutions for Dense Prediction in 3D
• Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation
• Relating the thermal properties of a micro pulsating heat pipe to the internal flow characteristics via experiments, image recognition of flow patterns and heat transfer simulations
• Continuous Conditional Random Field Convolution for Point Cloud Segmentation
• Efficient Video Object Segmentation via Network Modulation
• Semantic Edge Detection with Diverse Deep Supervision
• Fully Convolutional Networks for Chip-wise Defect Detection Employing Photoluminescence Images
• LDNet: End-to-End Lane Marking Detection Approach Using a Dynamic Vision Sensor
• COCO-Stuff: Thing and Stuff Classes in Context
• Towards High-Resolution Salient Object Detection
• Learning Depth with Convolutional Spatial Propagation Network
• Fine-Grained Crowd Counting
• Crowd Counting with Deep Structured Scale Integration Network
• Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features
• A Low-Cost, Flexible and Portable Volumetric Capturing System
• MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
• Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform
• Guided Anisotropic Diffusion and Iterative Learning for Weakly Supervised Change Detection
• Interactive Video Object Segmentation in the Wild
• A Context-aware Delayed Agglomeration Framework for Electron Microscopy Segmentation
• Exploring Feature Representation Learning for Semi-supervised Medical Image Segmentation
• Just-in-Time Reconstruction: Inpainting Sparse Maps using Single View Depth Predictors as Priors
• An Analysis of Pre-Training on Object Detection
• Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Study
• Pixel-Level Clustering Network for Unsupervised Image Segmentation
• Camouflaged Object Segmentation with Distraction Mining
• Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
• Face Parsing via a Fully-Convolutional Continuous CRF Neural Network
• BoxNet: Deep Learning Based Biomedical Image Segmentation Using Boxes Only Annotation
• DeepMVS: Learning Multi-view Stereopsis
• Simple Does It: Weakly Supervised Instance and Semantic Segmentation
• Pieces-of-parts for supervoxel segmentation with global context: Application to DCE-MRI tumour delineation
• Exploiting saliency for object segmentation from image level labels
• Monocular Depth Estimation using Multi-Scale Continuous CRFs as Sequential Deep Networks
• Pixel-wise Distance Regression for Glacier Calving Front Detection and Segmentation
• Co-salient Object Detection Based on Deep Saliency Networks and Seed Propagation over an Integrated Graph
• Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation
• Boundary-aware Supervoxel-level Iteratively Refined Interactive 3D Image Segmentation with Multi-agent Reinforcement Learning
• ASMCNN: An Efficient Brain Extraction Using Active Shape Model and Convolutional Neural Networks
• Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector
• Semi-supervised Body Parsing and Pose Estimation for Enhancing Infant General Movement Assessment
• BoxInst: High-Performance Instance Segmentation with Box Annotations
• Deeply Learning the Messages in Message Passing Inference
• Getting to 99% Accuracy in Interactive Segmentation
• Video Propagation Networks
• Iterative Visual Reasoning Beyond Convolutions
• Metastatic liver tumour segmentation from discriminant Grassmannian manifolds
• Learning Dense Correspondence via 3D-guided Cycle Consistency
• A Comparison and Strategy of Semantic Segmentation on Remote Sensing Images
• RESA: Recurrent Feature-Shift Aggregator for Lane Detection
• Learning Affinity via Spatial Propagation Networks
• Transformer-Unet: Raw Image Processing with Unet
• A Survey on Deep Learning Architectures for Image-based Depth Reconstruction
• Local Label Point Correction for Edge Detection of Overlapping Cervical Cells
• Exploiting Shape Cues for Weakly Supervised Semantic Segmentation
• Discriminative Training of Deep Fully-connected Continuous CRF with Task-specific Loss
• A Multi-scale CNN-CRF Framework for Environmental Microorganism Image Segmentation
• Lucid Data Dreaming for Video Object Segmentation
• Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation
• InstanceCut: from Edges to Instances with MultiCut
• X-volution: On the unification of convolution and self-attention
• Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer
• Image Segmentation via Probabilistic Graph Matching
• Holistic, Instance-Level Human Parsing
• Deep Multiphase Level Set for Scene Parsing
• Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey
• Large-Field Contextual Feature Learning for Glass Detection
• Improving Fully Convolution Network for Semantic Segmentation
• Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation
• One-view occlusion detection for stereo matching with a fully connected CRF model
• Semantic Motion Segmentation Using Dense CRF Formulation
• LEGO: Learning Edge with Geometry all at Once by Watching Videos
• Residual Pyramid Learning for Single-Shot Semantic Segmentation
• A Novel Upsampling and Context Convolution for Image Semantic Segmentation
• Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs
• Gated Feedback Refinement Network for Coarse-to-Fine Dense Semantic Image Labeling
• YouTube-VOS: Sequence-to-Sequence Video Object Segmentation
• Pixel-Adaptive Convolutional Neural Networks
• Selectivity or Invariance: Boundary-aware Salient Object Detection
• Learning Video Object Segmentation from Unlabeled Videos
• Deep Learning Markov Random Field for Semantic Segmentation
• Full-Duplex Strategy for Video Object Segmentation
• On Regularized Losses for Weakly-supervised CNN Segmentation
• Hyperspectral Image Classification with Deep Metric Learning and Conditional Random Field
• Weakly Supervised Change Detection Using Guided Anisotropic Difusion
• Online Flocking Control of UAVs with Mean-Field Approximation
• Online Unsupervised Video Object Segmentation via Contrastive Motion Clustering
• Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery
• Feature Pyramid Encoding Network for Real-time Semantic Segmentation
• Counterfactual Critic Multi-Agent Training for Scene Graph Generation
• Multi-View Deep Learning for Consistent Semantic Mapping with RGB-D Cameras
• Learning the Matching Function
• Disentangled High Quality Salient Object Detection
• Semi-Supervised Self-Taught Deep Learning for Finger Bones Segmentation
• Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts
• Scene Graph Generation via Conditional Random Fields
• Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization
• Iterative Instance Segmentation
• Learning Dense Convolutional Embeddings for Semantic Segmentation
• LabelBank: Revisiting Global Perspectives for Semantic Segmentation
• Referring Relationships
• Richer and Deeper Supervision Network for Salient Object Detection
• Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
• CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement
• Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision
• Temporal Convolutional Networks: A Unified Approach to Action Segmentation
• Change Detection in Multi-temporal VHR Images Based on Deep Siamese Multi-scale Convolutional Networks
• Action Genome: Actions as Composition of Spatio-temporal Scene Graphs
• Shallow2Deep: Indoor Scene Modeling by Single Image Understanding
• Motion Guided Attention for Video Salient Object Detection
• Saliency Integration: An Arbitrator Model
• PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things
• Object-aware Contrastive Learning for Debiased Scene Representation
• Conditional Random Fields as Recurrent Neural Networks for 3D Medical Imaging Segmentation
• PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image
• A Smartphone based Application for Skin Cancer Classification Using Deep Learning with Clinical Images and Lesion Information
• Optical Flow with Semantic Segmentation and Localized Layers
• Adaptive Masked Proxies for Few-Shot Segmentation
• Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation
• Accurate 3D Cell Segmentation using Deep Feature and CRF Refinement
• Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds
• Instance Embedding Transfer to Unsupervised Video Object Segmentation
• Correlation Maximized Structural Similarity Loss for Semantic Segmentation
• Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation
• Weakly-supervised Learning For Catheter Segmentation in 3D Frustum Ultrasound
• Convolutional Random Walk Networks for Semantic Image Segmentation
• Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation
• Move to See Better: Self-Improving Embodied Object Detection
• AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?
• Modeling the Background for Incremental and Weakly-Supervised Semantic Segmentation
• Deep GrabCut for Object Selection
• Accurate RGB-D Salient Object Detection via Collaborative Learning
• Semantic Video Segmentation by Gated Recurrent Flow Propagation
• SegFix: Model-Agnostic Boundary Refinement for Segmentation
• PolyTransform: Deep Polygon Transformer for Instance Segmentation
• SE2Net: Siamese Edge-Enhancement Network for Salient Object Detection
• StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction
• Extracting Lungs from CT Images using Fully Convolutional Networks
• Context-Aware Mixed Reality: A Framework for Ubiquitous Interaction
• Adaptive Affinity Fields for Semantic Segmentation
• Deep Outdoor Illumination Estimation
• Unsupervised Total Variation Loss for Semi-supervised Deep Learning of Semantic Segmentation
• Exploring Context with Deep Structured models for Semantic Segmentation
• Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net
• DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervision
• Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation
• Deformable kernel networks for guided depth map upsampling
• Weakly-supervised Salient Instance Detection
• Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes
• Learning Motion and Temporal Cues for Unsupervised Video Object Segmentation
• Boundary-preserving Mask R-CNN
• Movable-Object-Aware Visual SLAM via Weakly Supervised Semantic Segmentation
• Learning Deep Representations for Semantic Image Parsing: a Comprehensive Overview
• Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up
• Learning to Predict Indoor Illumination from a Single Image
• Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs
• Ultra Fast Structure-aware Deep Lane Detection
• Dual Convolutional Neural Networks for Breast Mass Segmentation and Diagnosis in Mammography
• A Bottom-up Approach for Pancreas Segmentation using Cascaded Superpixels and (Deep) Image Patch Labeling
• Cystoid macular edema segmentation of Optical Coherence Tomography images using fully convolutional neural networks and fully connected CRFs
• Semantic Correlation Promoted Shape-Variant Context for Segmentation
• Three Birds One Stone: A General Architecture for Salient Object Segmentation, Edge Detection and Skeleton Extraction
• Optimizing the F-measure for Threshold-free Salient Object Detection
• Two layer Ensemble of Deep Learning Models for Medical Image Segmentation
• Weakly-Supervised Semantic Segmentation via Sub-category Exploration
• Locate then Segment: A Strong Pipeline for Referring Image Segmentation
• Top-Down Learning for Structured Labeling with Convolutional Pseudoprior
• A Deep Primal-Dual Network for Guided Depth Super-Resolution
• Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation
• Adversarial Deep Structured Nets for Mass Segmentation from Mammograms
• Affinity LCFCN: Learning to Segment Fish with Weak Supervision
• Efficient Deep Neural Networks
• A Survey on Deep Learning Methods for Semantic Image Segmentation in Real-Time
• Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network
• FoveaNet: Perspective-aware Urban Scene Parsing
• Linguistic Structure Guided Context Modeling for Referring Image Segmentation
• Geometric Scene Parsing with Hierarchical LSTM
• Segmenting Objects in Day and Night:Edge-Conditioned CNN for Thermal Image Semantic Segmentation
• Self-explanatory Deep Salient Object Detection
• Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation
• Inference tools for Markov Random Fields on lattices: The R package mrf2d
• Fast End-to-End Trainable Guided Filter
• A Gap-Based Framework for Chinese Word Segmentation via Very Deep Convolutional Networks
• Tree-structured Kronecker Convolutional Network for Semantic Segmentation
• Real-time Progressive 3D Semantic Segmentation for Indoor Scene
• A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-view Stereo Reconstruction from An Open Aerial Dataset
• Asynchronous Temporal Fields for Action Recognition
• Min-max Entropy for Weakly Supervised Pointwise Localization
• Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers
• Efficient SDP Inference for Fully-connected CRFs Based on Low-rank Decomposition
• Efficient Coarse-to-Fine Non-Local Module for the Detection of Small Objects
• Mask Propagation Network for Video Object Segmentation
• Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning
• A Robotic 3D Perception System for Operating Room Environment Awareness
• An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images
• Fast Semantic Image Segmentation with High Order Context and Guided Filtering
• Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer
• Layered Interpretation of Street View Images
• Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation
• WebSeg: Learning Semantic Segmentation from Web Searches
• Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection
• Detailed Dense Inference with Convolutional Neural Networks via Discrete Wavelet Transform
• Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning
• Unifying Training and Inference for Panoptic Segmentation
• PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Mask
• Fuzzy Semantic Segmentation of Breast Ultrasound Image with Breast Anatomy Constraints
• Multi-Stage Pathological Image Classification using Semantic Segmentation
• Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images
• Uncertainty Inspired RGB-D Saliency Detection
• Uncertainty-based graph convolutional networks for organ segmentation refinement
• Learning High-level Prior with Convolutional Neural Networks for Semantic Segmentation
• End-to-End Training of Hybrid CNN-CRF Models for Stereo
• DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks
• Dense Recurrent Neural Networks for Scene Labeling
• Structured Output Learning with Conditional Generative Flows
• Deep Neural Networks for Surface Segmentation Meet Conditional Random Fields
• PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image
• Global Hypothesis Generation for 6D Object Pose Estimation
• Automatic Foreground Extraction from Imperfect Backgrounds using Multi-Agent Consensus Equilibrium
• Error Correction for Dense Semantic Image Labeling
• Semantic Segmentation by Improved Generative Adversarial Networks
• Learning Tubule-Sensitive CNNs for Pulmonary Airway and Artery-Vein Segmentation in CT
• Visual-Inertial-Semantic Scene Representation for 3-D Object Detection
• Unsupervised Moving Object Detection via Contextual Information Separation
• Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume
• An Underwater Image Semantic Segmentation Method Focusing on Boundaries and a Real Underwater Scene Semantic Segmentation Dataset
• Structured Feature Learning for Pose Estimation
• Importance Sampling CAMs for Weakly-Supervised Segmentation
• Object Discovery in Videos as Foreground Motion Clustering
• Adaptive Early-Learning Correction for Segmentation from Noisy Annotations
• Deep Feature Factorization For Concept Discovery
• Accurate Weakly-Supervised Deep Lesion Segmentation using Large-Scale Clinical Annotations: Slice-Propagated 3D Mask Generation from 2D RECIST
• Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation
• HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding
• Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task
• DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
• Actor-Action Semantic Segmentation with Grouping Process Models
• Can Ground Truth Label Propagation from Video help Semantic Segmentation?
• Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection
• Spectral Geometric Matrix Completion
• VigDet: Knowledge Informed Neural Temporal Point Process for Coordination Detection on Social Media
• Beyond Forward Shortcuts: Fully Convolutional Master-Slave Networks (MSNets) with Backward Skip Connections for Semantic Segmentation
• A Regularized Convolutional Neural Network for Semantic Image Segmentation
• Value of Temporal Dynamics Information in Driving Scene Segmentation
• Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation
• Photo Wake-Up: 3D Character Animation from a Single Photo
• Extreme View Synthesis
• Pseudo Mask Augmented Object Detection
• Improving Semantic Segmentation via Dilated Affinity
• Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks
• Applications of Deep Learning in Fundus Images: A Review
• Meticulous Object Segmentation
• Stacked Neural Networks for end-to-end ciliary motion analysis
• A Projected Gradient Descent Method for CRF Inference allowing End-To-End Training of Arbitrary Pairwise Potentials
• To Relieve Your Headache of Training an MRF, Take AdVIL
• Deep Stereo Matching with Dense CRF Priors
• Geo-Supervised Visual Depth Prediction
• Frame-To-Frame Consistent Semantic Segmentation
• Neuron-level Selective Context Aggregation for Scene Segmentation
• Learning Motion Patterns in Videos
• A Classification Refinement Strategy for Semantic Segmentation
• ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
• Boosting Few-shot Semantic Segmentation with Transformers
• ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings
• Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation
• Mixed context networks for semantic segmentation
• Scene Labeling using Gated Recurrent Units with Explicit Long Range Conditioning
• Causal Unsupervised Semantic Segmentation
• Pushing the Limits of Deep CNNs for Pedestrian Detection
• Car Segmentation and Pose Estimation using 3D Object Models
• Superpixel Convolutional Networks using Bilateral Inceptions
• Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-segmentation
• Tsanet: Temporal and Scale Alignment for Unsupervised Video Object Segmentation
• Composition-Aware Image Aesthetics Assessment
• ContinuityLearner: Geometric Continuity Feature Learning for Lane Segmentation
• Fast Object Segmentation Learning with Kernel-based Methods for Robotics
• High-order Semantic Role Labeling
• Bipartite Conditional Random Fields for Panoptic Segmentation
• An Integrated Image Filter for Enhancing Change Detection Results
• Automatically Extract the Semi-transparent Motion-blurred Hand from a Single Image
• Hard Pixel Mining for Depth Privileged Semantic Segmentation
• Data Priming Network for Automatic Check-Out
• Efficient Full Image Interactive Segmentation by Leveraging Within-image Appearance Similarity
• Image Labeling with Markov Random Fields and Conditional Random Fields
• Hierarchical Protein Function Prediction with Tail-GNNs
• Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation
• Referring Image Segmentation via Cross-Modal Progressive Comprehension
• Meta Learning with Differentiable Closed-form Solver for Fast Video Object Segmentation
• A New Local Transformation Module for Few-shot Segmentation
• Contrast-Oriented Deep Neural Networks for Salient Object Detection
• Adversarial Framework for Unsupervised Learning of Motion Dynamics in Videos
• 3D Randomized Connection Network with Graph-based Label Inference
• Visual Semantic Information Pursuit: A Survey
• Fully Using Classifiers for Weakly Supervised Semantic Segmentation with Modified Cues
• Spatial Memory for Context Reasoning in Object Detection
• Learning Fully Dense Neural Networks for Image Semantic Segmentation
• High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits
• Pixelwise Instance Segmentation with a Dynamically Instantiated Network
• An Artificial Intelligence-Based System for Nutrient Intake Assessment of Hospitalised Patients
• ViP-CNN: Visual Phrase Guided Convolutional Neural Network
• Rethinking Convolutional Semantic Segmentation Learning
• Conditional Random Field and Deep Feature Learning for Hyperspectral Image Segmentation
• A deep-structured fully-connected random field model for structured inference
• Balancing Appearance and Context in Sketch Interpretation
• Structured Depth Prediction in Challenging Monocular Video Sequences
• Semantic Segmentation with Boundary Neural Fields
• Perturb-and-MPM: Quantifying Segmentation Uncertainty in Dense Multi-Label CRFs
• Multi-source weak supervision for saliency detection
• Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing
• Constrained Convolutional Neural Networks for Weakly Supervised Segmentation
• Learning Predicates as Functions to Enable Few-shot Scene Graph Prediction
• Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation
• Representative Graph Neural Network
• Automatic Real-time Background Cut for Portrait Videos
• Weakly Supervised Body Part Segmentation with Pose based Part Priors
• Weakly- and Semi-Supervised Panoptic Segmentation
• Belief Propagation in Conditional RBMs for Structured Prediction
• Fast and Accurate Online Video Object Segmentation via Tracking Parts
• Weakly Supervised Minirhizotron Image Segmentation with MIL-CAM
• CLASS: Cross-Level Attention and Supervision for Salient Objects Detection
• Kinematic-Layout-aware Random Forests for Depth-based Action Recognition
• Two-stage Visual Cues Enhancement Network for Referring Image Segmentation
• Processing and Segmentation of Human Teeth from 2D Images using Weakly Supervised Learning
• Saliency guided deep network for weakly-supervised image segmentation
• Arabidopsis roots segmentation based on morphological operations and CRFs
• A Novel Deep Learning Based Approach for Left Ventricle Segmentation in Echocardiography: MFP-Unet
• Deep Learning for Automated Medical Image Analysis
• Transductive Few-Shot Learning: Clustering is All You Need?
• WhoAmI: An Automatic Tool for Visual Recognition of Tiger and Leopard Individuals in the Wild
• Boundary-Aware Salient Object Detection via Recurrent Two-Stream Guided Refinement Network
• Probabilistic Discriminative Learning with Layered Graphical Models
• Learnable Histogram: Statistical Context Features for Deep Neural Networks
• EarthMapper: A Tool Box for the Semantic Segmentation of Remote Sensing Imagery
• A Two-step Surface-based 3D Deep Learning Pipeline for Segmentation of Intracranial Aneurysms
• Dynamic Video Segmentation Network
• Diverse Sampling for Self-Supervised Learning of Semantic Segmentation
• SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes
• Instance-Level Salient Object Segmentation
• Manifold-driven Attention Maps for Weakly Supervised Segmentation
• Learning Dynamic Hierarchical Models for Anytime Scene Labeling
• Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation
• HR-RCNN: Hierarchical Relational Reasoning for Object Detection
• Detect, Replace, Refine: Deep Structured Prediction For Pixel Wise Labeling
• Post Processing of image segmentation using Conditional Random Fields
• Monocular Spherical Depth Estimation with Explicitly Connected Weak Layout Cues
• Self-supervised Segmentation via Background Inpainting
• 3D Shape Segmentation with Geometric Deep Learning
• Better Image Segmentation by Exploiting Dense Semantic Predictions
• Scene Parsing via Dense Recurrent Neural Networks with Attentional Selection
• Graph-FCN for image semantic segmentation
• 3D Guided Weakly Supervised Semantic Segmentation
• Beyond Pixels: A Comprehensive Survey from Bottom-up to Semantic Image Segmentation and Cosegmentation
• CrowdCam: Dynamic Region Segmentation
• Refining Semantic Segmentation with Superpixel by Transparent Initialization and Sparse Encoder
• Development of Conditional Random Field Insert for UNet-based Zonal Prostate Segmentation on T2-Weighted MRI
• A Weakly Supervised Convolutional Network for Change Segmentation and Classification
• Framework-agnostic Semantically-aware Global Reasoning for Segmentation
• Hair Segmentation on Time-of-Flight RGBD Images
• Human Centred Object Co-Segmentation
• Scaling Matters in Deep Structured-Prediction Models
• Deep Neural Networks In Fully Connected CRF For Image Labeling With Social Network Metadata
• Semantic-Aware Depth Super-Resolution in Outdoor Scenes
• Deeply Exploit Depth Information for Object Detection
• Weakly supervised semantic segmentation of tomographic images in the diagnosis of stroke
• Progressively Diffused Networks for Semantic Image Segmentation
• Superpixel-enhanced Pairwise Conditional Random Field for Semantic Segmentation
• An Artificial Intelligence-Based System to Assess Nutrient Intake for Hospitalised Patients
• Action Understanding with Multiple Classes of Actors
• DeepStrip: High Resolution Boundary Refinement
• A Tiered Move-making Algorithm for General Non-submodular Pairwise Energies
• ICE-GAN: Identity-aware and Capsule-Enhanced GAN with Graph-based Reasoning for Micro-Expression Recognition and Synthesis
• Ro-SOS: Metric Expression Network (MEnet) for Robust Salient Object Segmentation
• Deep, Dense, and Low-Rank Gaussian Conditional Random Fields
• Object Boundary Guided Semantic Segmentation
• Stereo Matching by Joint Energy Minimization
• Principled Parallel Mean-Field Inference for Discrete Random Fields
• Cross-Modal Progressive Comprehension for Referring Segmentation
• Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation
• Defocus Blur Detection via Depth Distillation
• Person re-identification via efficient inference in fully connected CRF
• Adversarial Learning for Image Forensics Deep Matching with Atrous Convolution
• Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network
• Generating Self-Guided Dense Annotations for Weakly Supervised Semantic Segmentation
• Automatic Image Labelling at Pixel Level
• Understand, Compose and Respond - Answering Visual Questions by a Composition of Abstract Procedures
• RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation
• Bayesian Convolutional Neural Networks for Compressed Sensing Restoration
• GlassNet: Label Decoupling-based Three-stream Neural Network for Robust Image Glass Detection
• Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models
• Structured Context Enhancement Network for Mouse Pose Estimation
• Multi-scale Interactive Network for Salient Object Detection
• Weakly Supervised Image Annotation and Segmentation with Objects and Attributes
• Sequential Labeling with online Deep Learning
• Recurrent Multimodal Interaction for Referring Image Segmentation
• Probabilistic Semantic Segmentation Refinement by Monte Carlo Region Growing
• Learning Data-driven Reflectance Priors for Intrinsic Image Decomposition
• Adaptive ROI Generation for Video Object Segmentation Using Reinforcement Learning
• Soccer on Your Tabletop
• SiamParseNet: Joint Body Parsing and Label Propagation in Infant Movement Videos
• Complex Relations in a Deep Structured Prediction Model for Fine Image Segmentation
• Salient Instance Segmentation via Subitizing and Clustering
• Adversarial Structure Matching for Structured Prediction Tasks
• Policy Message Passing: A New Algorithm for Probabilistic Graph Inference
• CNN-based Semantic Segmentation using Level Set Loss
• Low-level Vision by Consensus in a Spatial Hierarchy of Regions
• RPM-Net: Robust Pixel-Level Matching Networks for Self-Supervised Video Object Segmentation
• Encoder-Decoder based CNN and Fully Connected CRFs for Remote Sensed Image Segmentation
• A Multi-Layer Approach to Superpixel-based Higher-order Conditional Random Field for Semantic Image Segmentation
• Blending Learning and Inference in Structured Prediction
• Iteratively-Refined Interactive 3D Medical Image Segmentation with Multi-Agent Reinforcement Learning
• Automatic Video Object Segmentation via Motion-Appearance-Stream Fusion and Instance-aware Segmentation
• End-to-end Training of CNN-CRF via Differentiable Dual-Decomposition
• Tackling the Problem of Limited Data and Annotations in Semantic Segmentation
• Quantization in Relative Gradient Angle Domain For Building Polygon Estimation
• CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF
• Zoom in to the details of human-centric videos
• MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models
• Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread
• Forming A Random Field via Stochastic Cliques: From Random Graphs to Fully Connected Random Fields
• Robust Trust Region for Weakly Supervised Segmentation
• Weakly-Supervised Image Semantic Segmentation Using Graph Convolutional Networks
• Region Refinement Network for Salient Object Detection
• Learning to segment with image-level supervision
• High-fidelity Pseudo-labels for Boosting Weakly-Supervised Segmentation
• ROSA: Robust Salient Object Detection against Adversarial Attacks
• DOPE: Distributed Optimization for Pairwise Energies
• Closed-Loop Adaptation for Weakly-Supervised Semantic Segmentation
• Multi-Scale Convolutions for Learning Context Aware Feature Representations
• Pixel-wise Segmentation of Right Ventricle of Heart
• Atlas-aware ConvNetfor Accurate yet Robust Anatomical Segmentation
• Learning Rich Representations For Structured Visual Prediction Tasks
• Vessel-CAPTCHA: an efficient learning framework for vessel annotation and segmentation
• Interpreting Deep Neural Networks with Relative Sectional Propagation by Analyzing Comparative Gradients and Hostile Activations
• Distortion-adaptive Salient Object Detection in 360${}^{\circ }$ Omnidirectional Images
• Fast and Differentiable Message Passing on Pairwise Markov Random Fields
• Video Semantic Object Segmentation by Self-Adaptation of DCNN
• Supervised Hashing based on Energy Minimization
• Per-Pixel Feedback for improving Semantic Segmentation
• Context Tricks for Cheap Semantic Segmentation
• Salient Object Detection with Purificatory Mechanism and Structural Similarity Loss
• Worst-case Optimal Submodular Extensions for Marginal Estimation
• Free Lunch for Co-Saliency Detection: Context Adjustment
• An Abstraction Model for Semantic Segmentation Algorithms
• Weakly Supervised Instance Segmentation by Deep Community Learning
• PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation
• Gland Instance Segmentation by Deep Multichannel Side Supervision
• Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP
• Region-based semantic segmentation with end-to-end training
• Realizing Pixel-Level Semantic Learning in Complex Driving Scenes based on Only One Annotated Pixel per Class
• Differentiable Projection for Constrained Deep Learning
• Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs
• Efficient Continuous Relaxations for Dense CRF
• A Holistic Approach for Data-Driven Object Cutout
• Variational reaction-diffusion systems for semantic segmentation
• 3D Iterative Spatiotemporal Filtering for Classification of Multitemporal Satellite Data Sets
• Dense Semantic Correspondence where Every Pixel is a Classifier
• CMF: Cascaded Multi-model Fusion for Referring Image Segmentation
• Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation
• Pseudo Pixel-level Labeling for Images with Evolving Content
• AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network
• Do End-to-end Stereo Algorithms Under-utilize Information?
• Beyond Gradient Descent for Regularized Segmentation Losses
• Automatic Airway Segmentation in chest CT using Convolutional Neural Networks
• Accelerated Inference in Markov Random Fields via Smooth Riemannian Optimization
• Deep nested level sets: Fully automated segmentation of cardiac MR images in patients with pulmonary hypertension
• Learning Pixel Representations for Generic Segmentation
• MoE-SPNet: A Mixture-of-Experts Scene Parsing Network
• Learning Propagation for Arbitrarily-structured Data