Semantic Image Segmentation via Deep Parsing Network
arXiv:1509.02634
Abstract
This paper addresses semantic image segmentation by incorporating rich information into Markov Random Field (MRF), including high-order relations and mixture of label contexts. Unlike previous works that optimized MRFs using iterative algorithm, we solve MRF by proposing a Convolutional Neural Network (CNN), namely Deep Parsing Network (DPN), which enables deterministic end-to-end computation in a single forward pass. Specifically, DPN extends a contemporary CNN architecture to model unary terms and additional layers are carefully devised to approximate the mean field algorithm (MF) for pairwise terms. It has several appealing properties. First, different from the recent works that combined CNN and MRF, where many iterations of MF were required for each training image during back-propagation, DPN is able to achieve high performance by approximating one iteration of MF. Second, DPN represents various types of pairwise terms, making many existing works as its special cases. Third, DPN makes MF easier to be parallelized and speeded up in Graphical Processing Unit (GPU). DPN is thoroughly evaluated on the PASCAL VOC 2012 dataset, where a single DPN model yields a new state-of-the-art segmentation accuracy.
arXiv commentTo appear in International Conference on Computer Vision (ICCV) 2015
References in corpus (11)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Distilling the Knowledge in a Neural Network
- Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- Fully Convolutional Networks for Semantic Segmentation
- Conditional Random Fields as Recurrent Neural Networks
- Deep Learning Face Representation by Joint Identification-Verification
- cuDNN: Efficient Primitives for Deep Learning
- Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
- Fully Connected Deep Structured Networks
- Efficient piecewise training of deep structured models for semantic segmentation
Cited by in corpus (84)
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
- Pyramid Scene Parsing Network
- Pyramid Attention Network for Semantic Segmentation
- Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
- Dual Attention Network for Scene Segmentation
- Training convolutional neural networks to estimate turbulent sub-grid scale reaction rates
- Context Encoding for Semantic Segmentation
- ICNet for Real-Time Semantic Segmentation on High-Resolution Images
- Learning a Discriminative Feature Network for Semantic Segmentation
- Efficient piecewise training of deep structured models for semantic segmentation
- Stacked Deconvolutional Network for Semantic Segmentation
- Semantic Facial Expression Editing using Autoencoded Flow
- Video Object Segmentation with Re-identification
- PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing
- RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
- Pushing the Boundaries of Boundary Detection using Deep Learning
- The Stixel world: A medium-level representation of traffic scenes
- Combining the Best of Convolutional Layers and Recurrent Layers: A Hybrid Network for Semantic Segmentation
- Attention guided global enhancement and local refinement network for semantic segmentation
- Deep Interactive Object Selection
- Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform
- Pixel-level Encoding and Depth Layering for Instance-level Semantic Labeling
- MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
- Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
- Semantic Object Parsing with Local-Global Long Short-Term Memory
- Weakly Supervised Semantic Segmentation using Web-Crawled Videos
- InstanceCut: from Edges to Instances with MultiCut
- Improving Fully Convolution Network for Semantic Segmentation
- DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation
- Knowledge Adaptation for Efficient Semantic Segmentation
- Evolutionary Synthesis of Deep Neural Networks via Synaptic Cluster-driven Genetic Encoding
- Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
- Scene Parsing with Global Context Embedding
- Semantic Video Segmentation by Gated Recurrent Flow Propagation
- Adaptive Affinity Fields for Semantic Segmentation
- Exploring Context with Deep Structured models for Semantic Segmentation
- Unsupervised Total Variation Loss for Semi-supervised Deep Learning of Semantic Segmentation
- Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net
- Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs
- Learning Deep Representations for Semantic Image Parsing: a Comprehensive Overview
- Reversible Recursive Instance-level Object Segmentation
- Tensor Low-Rank Reconstruction for Semantic Segmentation
- Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation
- Recent Advances in the Applications of Convolutional Neural Networks to Medical Image Contour Detection
- Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation
- Fast Semantic Image Segmentation with High Order Context and Guided Filtering
- CARAFE++: Unified Content-Aware ReAssembly of FEatures
- Deep Convolutional Neural Networks with Spatial Regularization, Volume and Star-shape Priori for Image Segmentation
- Surveillance Video Parsing with Single Frame Supervision
- Learning to Predict Context-adaptive Convolution for Semantic Segmentation
- Dense Recurrent Neural Networks for Scene Labeling
- End-to-End Training of Hybrid CNN-CRF Models for Stereo
- Deep Structured Scene Parsing by Learning with Image Descriptions
- Semantic Object Parsing with Graph LSTM
- Mix-and-Match Tuning for Self-Supervised Semantic Segmentation
- Multi-scale Attention U-Net (MsAUNet): A Modified U-Net Architecture for Scene Segmentation
- Pseudo Mask Augmented Object Detection
- SeGAN: Segmenting and Generating the Invisible
- A Projected Gradient Descent Method for CRF Inference allowing End-To-End Training of Arbitrary Pairwise Potentials
- Triply Supervised Decoder Networks for Joint Detection and Segmentation
- ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
- Superpixel Convolutional Networks using Bilateral Inceptions
- Scene Labeling using Gated Recurrent Units with Explicit Long Range Conditioning
- Low-Latency Video Semantic Segmentation
- Hard Pixel Mining for Depth Privileged Semantic Segmentation
- Bipartite Conditional Random Fields for Panoptic Segmentation
- Learning Deep Representations for Scene Labeling with Semantic Context Guided Supervision
- High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits
- Learnable Histogram: Statistical Context Features for Deep Neural Networks
- Improved Hard Example Mining by Discovering Attribute-based Hard Person Identity
- STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling
- Dense CNN Learning with Equivalent Mappings
- Robust and Efficient Graph Correspondence Transfer for Person Re-identification
- Multi-Level Contextual Network for Biomedical Image Segmentation
- Phase Contrast Microscopy Cell PopulationSegmentation: A Survey
- Progressively Diffused Networks for Semantic Image Segmentation
- Scene Parsing via Dense Recurrent Neural Networks with Attentional Selection
- Deep, Dense, and Low-Rank Gaussian Conditional Random Fields
- A Spatially Constrained Deep Convolutional Neural Network for Nerve Fiber Segmentation in Corneal Confocal Microscopic Images using Inaccurate Annotations
- RethNet: Object-by-Object Learning for Detecting Facial Skin Problems
- LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling
- Affinity Derivation and Graph Merge for Instance Segmentation