Conditional Random Fields as Recurrent Neural Networks

Abstract

Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level labelling tasks. One central issue in this methodology is the limited capacity of deep learning techniques to delineate visual objects. To solve this problem, we introduce a new form of convolutional neural network that combines the strengths of Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs)-based probabilistic graphical modelling. To this end, we formulate mean-field approximate inference for the Conditional Random Fields with Gaussian pairwise potentials as Recurrent Neural Networks. This network, called CRF-RNN, is then plugged in as a part of a CNN to obtain a deep network that has desirable properties of both CNNs and CRFs. Importantly, our system fully integrates CRF modelling with CNNs, making it possible to train the whole deep network end-to-end with the usual back-propagation algorithm, avoiding offline post-processing methods for object delineation. We apply the proposed method to the problem of semantic image segmentation, obtaining top results on the challenging Pascal VOC 2012 segmentation benchmark.

This paper is published in IEEE ICCV 2015

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• On the difficulty of training Recurrent Neural Networks
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
• Convolutional Feature Masking for Joint Object and Stuff Segmentation
• Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
• Fully Connected Deep Structured Networks
• Learning Deep Structured Models
• Deep Structured Output Learning for Unconstrained Text Recognition
• Efficient piecewise training of deep structured models for semantic segmentation

Cited by in corpus (338)

• 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
• LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation
• Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges
• ParseNet: Looking Wider to See Better
• A deep learning model integrating FCNNs and CRFs for brain tumor segmentation
• Deep neural network models for computational histopathology: A survey
• Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields
• STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
• A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation
• A Survey on Instance Segmentation: State of the art
• Discriminative Embeddings of Latent Variable Models for Structured Data
• Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeries
• Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation
• Integrating Spatial Configuration into Heatmap Regression Based CNNs for Landmark Localization
• CCNet: Criss-Cross Attention for Semantic 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
• Loss Functions and Metrics in Deep Learning
• A Topological Loss Function for Deep-Learning based Image Segmentation using Persistent Homology
• Deep Vessel Segmentation By Learning Graphical Connectivity
• Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering
• A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images
• Deep Learning for Generic Object Detection: A Survey
• Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes
• FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
• InversionNet: A Real-Time and Accurate Full Waveform Inversion with CNNs and continuous CRFs
• Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
• Automatic skin lesion segmentation with fully convolutional-deconvolutional networks
• Semantic Image Segmentation via Deep Parsing Network
• Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks
• Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation
• Vehicle Instance Segmentation from Aerial Image and Video Using a Multi-Task Learning Residual Fully Convolutional Network
• A Taxonomy of Deep Convolutional Neural Nets for Computer Vision
• Generative Adversarial Networks and Conditional Random Fields for Hyperspectral Image Classification
• Non-local Neural Networks
• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
• Deformable Kernel Networks for Joint Image Filtering
• Learning Deep Representations of Fine-grained Visual Descriptions
• MirrorNet: Bio-Inspired Camouflaged Object Segmentation
• ToolNet: Holistically-Nested Real-Time Segmentation of Robotic Surgical Tools
• Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey
• Learning to Segment from Scribbles using Multi-scale Adversarial Attention Gates
• Dual Graph Convolutional Network for Semantic Segmentation
• BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
• Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
• Learning Deep Structured Models
• Buildings Detection in VHR SAR Images Using Fully Convolution Neural Networks
• Graph Attention Layer Evolves Semantic Segmentation for Road Pothole Detection: A Benchmark and Algorithms
• Going in circles is the way forward: the role of recurrence in visual inference
• Automatic Discovery and Geotagging of Objects from Street View Imagery
• Efficient Deep Learning of Non-local Features for Hyperspectral Image Classification
• Facial Action Unit Detection Using Attention and Relation Learning
• Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation
• Learning to Optimize: A Primer and A Benchmark
• Deep Continuous Conditional Random Fields with Asymmetric Inter-object Constraints for Online Multi-object Tracking
• Adaptive Morphological Reconstruction for Seeded Image Segmentation
• Deep Crisp Boundaries: From Boundaries to Higher-level Tasks
• Flowing ConvNets for Human Pose Estimation in Videos
• High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks
• Deep and Statistical Learning in Biomedical Imaging: State of the Art in 3D MRI Brain Tumor Segmentation
• A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning
• Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
• Angle-Closure Detection in Anterior Segment OCT based on Multi-Level Deep Network
• Asymmetric Non-local Neural Networks for Semantic Segmentation
• A Multi-Level Approach to Waste Object Segmentation
• Recurrent Neural Networks to Correct Satellite Image Classification Maps
• Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation
• Depth Adaptive Deep Neural Network for Semantic Segmentation
• Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation
• XNet: A convolutional neural network (CNN) implementation for medical X-Ray image segmentation suitable for small datasets
• Discriminative Feature Learning with Foreground Attention for Person Re-Identification
• Building Footprint Generation by IntegratingConvolution Neural Network with Feature PairwiseConditional Random Field (FPCRF)
• A Survey of Semantic Segmentation
• PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing
• FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction
• Gastric histopathology image segmentation using a hierarchical conditional random field
• Affinity Space Adaptation for Semantic Segmentation Across Domains
• DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
• Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation
• Random Forest with Learned Representations for Semantic Segmentation
• Video Semantic Segmentation with Distortion-Aware Feature Correction
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• Prior Guided Feature Enrichment Network for Few-Shot Segmentation
• A fully end-to-end deep learning approach for real-time simultaneous 3D reconstruction and material recognition
• LatentGNN: Learning Efficient Non-local Relations for Visual Recognition
• Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach
• Distance transform regression for spatially-aware deep semantic segmentation
• Addressing Overfitting on Pointcloud Classification using Atrous XCRF
• Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
• A Comprehensive Review of Modern Object Segmentation Approaches
• The Stixel world: A medium-level representation of traffic scenes
• 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
• Continuous Conditional Random Field Convolution for Point Cloud Segmentation
• Fine-Grained Crowd Counting
• Crowd Counting with Deep Structured Scale Integration Network
• Forecasting User Attention During Everyday Mobile Interactions Using Device-Integrated and Wearable Sensors
• Facial Action Unit Detection via Adaptive Attention and Relation
• A Review of 1D Convolutional Neural Networks toward Unknown Substance Identification in Portable Raman Spectrometer
• A Recurrent Encoder-Decoder Network for Sequential Face Alignment
• PDNet: Semantic Segmentation integrated with a Primal-Dual Network for Document binarization
• Gated Path Selection Network for Semantic Segmentation
• Quantitative reconstruction of defects in multi-layered bonded composites using fully convolutional network-based ultrasonic inversion
• SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
• I2F: A Unified Image-to-Feature Approach for Domain Adaptive Semantic Segmentation
• Deeply Learning the Messages in Message Passing Inference
• Improving BERT Performance for Aspect-Based Sentiment Analysis
• P2AT: Pyramid Pooling Axial Transformer for Real-time Semantic Segmentation
• Accurate Retinal Vessel Segmentation via Octave Convolution Neural Network
• ModaNet: A Large-Scale Street Fashion Dataset with Polygon Annotations
• Transformer-Unet: Raw Image Processing with Unet
• Como funciona o Deep Learning
• Segmenting Transparent Object in the Wild with Transformer
• Reasoning Visual Dialogs with Structural and Partial Observations
• RSI-Net: Two-Stream Deep Neural Network for Remote Sensing Imagesbased Semantic Segmentation
• A Multi-scale CNN-CRF Framework for Environmental Microorganism Image Segmentation
• Discriminative Training of Deep Fully-connected Continuous CRF with Task-specific Loss
• Attention-based Context Aggregation Network for Monocular Depth Estimation
• Depth-aware Blending of Smoothed Images for Bokeh Effect Generation
• Image Segmentation via Probabilistic Graph Matching
• Deep Multiphase Level Set for Scene Parsing
• Spatial Pyramid Based Graph Reasoning for Semantic Segmentation
• Situation Recognition with Graph Neural Networks
• ORDNet: Capturing Omni-Range Dependencies for Scene Parsing
• Efficient Yet Deep Convolutional Neural Networks for Semantic Segmentation
• Squeeze-and-Attention Networks for Semantic Segmentation
• Deep Learning Markov Random Field for Semantic Segmentation
• Pixel-Adaptive Convolutional Neural Networks
• Gated Feedback Refinement Network for Coarse-to-Fine Dense Semantic Image Labeling
• Global Aggregation then Local Distribution for Scene Parsing
• Knowledge Adaptation for Efficient Semantic Segmentation
• Counterfactual Critic Multi-Agent Training for Scene Graph Generation
• A survey of Object Classification and Detection based on 2D/3D data
• Deep Neural Networks for Automatic Grain-matrix Segmentation in Plane and Cross-polarized Sandstone Photomicrographs
• Improving Semantic Segmentation via Decoupled Body and Edge Supervision
• Towards Efficient Scene Understanding via Squeeze Reasoning
• Face Mask Extraction in Video Sequence
• Vision Transformers: From Semantic Segmentation to Dense Prediction
• m2caiSeg: Semantic Segmentation of Laparoscopic Images using Convolutional Neural Networks
• UPSNet: A Unified Panoptic Segmentation Network
• Referring Relationships
• Dynamic Face Video Segmentation via Reinforcement Learning
• Iterative Instance Segmentation
• Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
• Egocentric Object Manipulation Graphs
• CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement
• Coarse-to-Fine Annotation Enrichment for Semantic Segmentation Learning
• DAG-Recurrent Neural Networks For Scene Labeling
• End-to-End Deep Structured Models for Drawing Crosswalks
• Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation
• Scene Parsing with Integration of Parametric and Non-parametric Models
• Learning to Group and Label Fine-Grained Shape Components
• A Relation-Augmented Fully Convolutional Network for Semantic Segmentation in Aerial Scenes
• Correlation Maximized Structural Similarity Loss for Semantic Segmentation
• End-to-End Learning Deep CRF models for Multi-Object Tracking
• Deep Object Co-Segmentation
• Push-the-Boundary: Boundary-aware Feature Propagation for Semantic Segmentation of 3D Point Clouds
• Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse Coding
• SegFix: Model-Agnostic Boundary Refinement for Segmentation
• Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes
• Dual Convolutional Neural Networks for Breast Mass Segmentation and Diagnosis in Mammography
• One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation
• Deformable kernel networks for guided depth map upsampling
• Semantic Foreground Inpainting from Weak Supervision
• Learning Instance Occlusion for Panoptic Segmentation
• Tensor Low-Rank Reconstruction for Semantic Segmentation
• Top-Down Learning for Structured Labeling with Convolutional Pseudoprior
• Two-phase Hair Image Synthesis by Self-Enhancing Generative Model
• PetroSurf3D - A Dataset for high-resolution 3D Surface Segmentation
• Semantic Correlation Promoted Shape-Variant Context for Segmentation
• Deep Affinity Net: Instance Segmentation via Affinity
• A Survey on Deep Learning Methods for Semantic Image Segmentation in Real-Time
• Multiview Detection with Feature Perspective Transformation
• Segmenting Transparent Objects in the Wild
• Efficient Deep Neural Networks
• PanoNet: Real-time Panoptic Segmentation through Position-Sensitive Feature Embedding
• Large-Scale Classification of Structured Objects using a CRF with Deep Class Embedding
• Image segmentation via Cellular Automata
• Real-time Progressive 3D Semantic Segmentation for Indoor Scene
• Neural Inverse Knitting: From Images to Manufacturing Instructions
• Building Footprint Extraction with Graph Convolutional Network
• Nonlinear Markov Random Fields Learned via Backpropagation
• Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation
• GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networks
• Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning
• Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection
• Learning Deep Gradient Descent Optimization for Image Deconvolution
• Fast Semantic Image Segmentation with High Order Context and Guided Filtering
• Deep Gaussian Conditional Random Field Network: A Model-based Deep Network for Discriminative Denoising
• DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks
• Learning to Predict Context-adaptive Convolution for Semantic Segmentation
• Domain adaptation for holistic skin detection
• Fuzzy Semantic Segmentation of Breast Ultrasound Image with Breast Anatomy Constraints
• Multi-hypothesis contextual modeling for semantic segmentation
• Global and Local Features through Gaussian Mixture Models on Image Semantic Segmentation
• Semantic Segmentation by Improved Generative Adversarial Networks
• Face Parsing with RoI Tanh-Warping
• Structured Feature Learning for Pose Estimation
• Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks
• Neural Weighted A*: Learning Graph Costs and Heuristics with Differentiable Anytime A*
• How to Efficiently Annotate Images for Best-Performing Deep Learning Based Segmentation Models: An Empirical Study with Weak and Noisy Annotations and Segment Anything Model
• PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image
• Deep Neural Networks for Surface Segmentation Meet Conditional Random Fields
• Structured Output Learning with Conditional Generative Flows
• Straight to Shapes: Real-time Detection of Encoded Shapes
• HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding
• Value of Temporal Dynamics Information in Driving Scene Segmentation
• Second-Order Semantic Dependency Parsing with End-to-End Neural Networks
• Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task
• Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation Models
• CTNet: Context-based Tandem Network for Semantic Segmentation
• GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer
• Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shifts
• Towards Real-Time Automatic Portrait Matting on Mobile Devices
• Straight to Shapes++: Real-time Instance Segmentation Made More Accurate
• Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network
• Improving Semantic Segmentation via Dilated Affinity
• Attentional Prototype Inference for Few-Shot Segmentation
• Meticulous Object Segmentation
• PageNet: Page Boundary Extraction in Historical Handwritten Documents
• Boosting Few-shot Semantic Segmentation with Transformers
• Superpixel based Class-Semantic Texton Occurrences for Natural Roadside Vegetation Segmentation
• Pushing the Limits of Deep CNNs for Pedestrian Detection
• CNN based texture synthesize with Semantic segment
• ShelfNet for Fast Semantic Segmentation
• Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularization
• High-order Semantic Role Labeling
• Visual Semantic Information Pursuit: A Survey
• TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency
• A Design Space Study for LISTA and Beyond
• Image Labeling with Markov Random Fields and Conditional Random Fields
• An Integrated Image Filter for Enhancing Change Detection Results
• Learning to Generate Synthetic 3D Training Data through Hybrid Gradient
• Hallucinating Optical Flow Features for Video Classification
• Automatically Extract the Semi-transparent Motion-blurred Hand from a Single Image
• Hard Pixel Mining for Depth Privileged Semantic Segmentation
• Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation
• Bipartite Conditional Random Fields for Panoptic Segmentation
• A synthetic dataset for deep learning
• Distance Guided Channel Weighting for Semantic Segmentation
• Building Segmentation through a Gated Graph Convolutional Neural Network with Deep Structured Feature Embedding
• Road Segmentation with Image-LiDAR Data Fusion
• Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision
• Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation
• HR-RCNN: Hierarchical Relational Reasoning for Object Detection
• Multimodal 3D Brain Tumor Segmentation with Adversarial Training and Conditional Random Field
• Weakly Supervised Body Part Segmentation with Pose based Part Priors
• Lung Segmentation in Chest X-rays with Res-CR-Net
• Taking a Deeper Look at the Inverse Compositional Algorithm
• Learning Discriminators as Energy Networks in Adversarial Learning
• Non-local Channel Aggregation Network for Single Image Rain Removal
• Causal Hidden Markov Model for Time Series Disease Forecasting
• Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks
• Learnable Histogram: Statistical Context Features for Deep Neural Networks
• Representative Graph Neural Network
• EfficientFCN: Holistically-guided Decoding for Semantic Segmentation
• Label Refinement with an Iterative Generative Adversarial Network for Boosting Retinal Vessel Segmentation
• 3D Shape Segmentation with Geometric Deep Learning
• Probabilistic Discriminative Learning with Layered Graphical Models
• Neural ODEs with stochastic vector field mixtures
• IMP: Instance Mask Projection for High Accuracy Semantic Segmentation of Things
• Diverse Sampling for Self-Supervised Learning of Semantic Segmentation
• OVSNet : Towards One-Pass Real-Time Video Object Segmentation
• Learning Stereo Matchability in Disparity Regression Networks
• A Structured Learning Approach with Neural Conditional Random Fields for Sleep Staging
• DCANet: Dense Context-Aware Network for Semantic Segmentation
• A Weakly Supervised Convolutional Network for Change Segmentation and Classification
• Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly Detection
• Lift-the-flap: what, where and when for context reasoning
• Context Prior for Scene Segmentation
• A Chain Graph Interpretation of Real-World Neural Networks
• Shape-aware Generative Adversarial Networks for Attribute Transfer
• S3-Net: A Fast and Lightweight Video Scene Understanding Network by Single-shot Segmentation
• Location-aware Upsampling for Semantic Segmentation
• Multiple Style-Transfer in Real-Time
• ACEnet: Anatomical Context-Encoding Network for Neuroanatomy Segmentation
• Graph-FCN for image semantic segmentation
• Co-Morbidity Exploration on Wearables Activity Data Using Unsupervised Pre-training and Multi-Task Learning
• Development of Conditional Random Field Insert for UNet-based Zonal Prostate Segmentation on T2-Weighted MRI
• Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
• Scaling Matters in Deep Structured-Prediction Models
• A Deep DUAL-PATH Network for Improved Mammogram Image Processing
• A Probabilistic Representation of Deep Learning
• Structured Convolutional Kernel Networks for Airline Crew Scheduling
• Deep Markov Random Field for Image Modeling
• End-to-End Learned Random Walker for Seeded Image Segmentation
• Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models
• Randomized Deep Structured Prediction for Discourse-Level Processing
• Stereo Matching by Joint Energy Minimization
• Refining Semantic Segmentation with Superpixel by Transparent Initialization and Sparse Encoder
• Bayesian Convolutional Neural Networks for Compressed Sensing Restoration
• A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection
• AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network
• Improving Shape Deformation in Unsupervised Image-to-Image Translation
• Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation
• Factorisation-based Image Labelling
• Learning to segment with image-level supervision
• 3D Scene Parsing via Class-Wise Adaptation
• Multilinear Map Layer: Prediction Regularization by Structural Constraint
• Atlas-aware ConvNetfor Accurate yet Robust Anatomical Segmentation
• BiCANet: Bi-directional Contextual Aggregating Network for Image Semantic Segmentation
• Veritatem Dies Aperit- Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach
• A Survey on Green Deep Learning
• Unsupervised Image Segmentation using Mutual Mean-Teaching
• Impoved RPN for Single Targets Detection based on the Anchor Mask Net
• Robust Trust Region for Weakly Supervised Segmentation
• Realizing Pixel-Level Semantic Learning in Complex Driving Scenes based on Only One Annotated Pixel per Class
• Beyond Gradient Descent for Regularized Segmentation Losses
• ROSA: Robust Salient Object Detection against Adversarial Attacks
• Time-Discounting Convolution for Event Sequences with Ambiguous Timestamps
• Fast and Differentiable Message Passing on Pairwise Markov Random Fields
• Multi-Modal Mean-Fields via Cardinality-Based Clamping
• A Brief Survey and an Application of Semantic Image Segmentation for Autonomous Driving
• Complex Relations in a Deep Structured Prediction Model for Fine Image Segmentation
• Zoom in to the details of human-centric videos
• Adversarial Structure Matching for Structured Prediction Tasks
• A Multi-View Dynamic Fusion Framework: How to Improve the Multimodal Brain Tumor Segmentation from Multi-Views?
• Variational reaction-diffusion systems for semantic segmentation
• Tackling the Problem of Limited Data and Annotations in Semantic Segmentation
• RethNet: Object-by-Object Learning for Detecting Facial Skin Problems
• A Parametric Top-View Representation of Complex Road Scenes
• ELKPPNet: An Edge-aware Neural Network with Large Kernel Pyramid Pooling for Learning Discriminative Features in Semantic Segmentation
• Deep Learning Meets SAR
• Gaussian Filter in CRF Based Semantic Segmentation
• Relational Neural Markov Random Fields
• Learning Pixel Representations for Generic Segmentation
• Learning Propagation for Arbitrarily-structured Data
• PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation
• Boundary-aware Graph Reasoning for Semantic Segmentation
• Graph cuts always find a global optimum for Potts models (with a catch)
• Tissue characterization based on the analysis on i3DUS data for diagnosis support in neurosurgery
• Do End-to-end Stereo Algorithms Under-utilize Information?
• Non-parametric Memory for Spatio-Temporal Segmentation of Construction Zones for Self-Driving