Segmentation
- Semantic Segmentation
- Instance Segmentation
- Panoptic Segmentation
- Video Segmentation
- Saliency Detection
Semantic Segmentation
2019
- CVPR 2019
- Object-aware Aggregation with Bidirectional Temporal Graph for Video Captioning
- Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation
- Cross-Modal Relationship Inference for Grounding Referring Expressions
- Face Parsing with RoI Tanh-Warping
- Speech2Face: Learning the Face Behind a Voice
- Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images [code]
- Budget-aware Semi-Supervised Semantic and Instance Segmentation [Workshop]
- DARNet: Deep Active Ray Network for Building Segmentation
- Zoom To Learn, Learn To Zoom
- A Simple Pooling-Based Design for Real-Time Salient Object Detection
- Pyramid Feature Attention Network for Saliency detection [code]
- Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation [code]
- Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning [code]
- SCOPS: Self-Supervised Co-Part Segmentation
- Panoptic Feature Pyramid Networks
- Representation Similarity Analysis for Efficient Task taxonomy & Transfer Learning [code]
- Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More
- Data-Driven Neuron Allocation for Scale Aggregation Networks
- Bi-Directional Cascade Network for Perceptual Edge Detection [code]
- Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation
- DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
- Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations
- Adaptive Weighting Multi-Field-of-View CNN for Semantic Segmentation in Pathology
- Pixel-Adaptive Convolutional Neural Networks
- A Relation-Augmented Fully Convolutional Network for Semantic Segmentation in Aerial Scenes
- Cross-Modal Self-Attention Network for Referring Image Segmentation [From NLP]
- Graphonomy: Universal Human Parsing via Graph Transfer Learning [code]
- Large-scale interactive object segmentation with human annotators
- In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images
- A Cross-Season Correspondence Dataset for Robust Semantic Segmentation
- Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation [code]
- Knowledge Adaptation for Efficient Semantic Segmentation
- Structured Knowledge Distillation for Semantic Segmentation
- FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference
- Data augmentation using learned transforms for one-shot medical image segmentation
- Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation
- Graph-Based Global Reasoning Networks [GCN]
- T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor [Face Part Seg]
- Improving Semantic Segmentation via Video Propagation and Label Relaxation
- other 19'conferences
- ICCV 2019
- Incremental Class Discovery for Semantic Segmentation with RGBD Sensing
- Asymmetric Non-local Neural Networks for Semantic Segmentation
- Exploiting temporal consistency for real-time video depth estimationโ
- Action recognition with spatial-temporal discriminative filter banks
- Temporal Knowledge Propagation for Image-to-Video Person Re-identification
- Semi-Supervised Video Salient Object Detection Using Pseudo-Labels
- LIP: Local Importance-based Pooling
- Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation
- Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings [code]
- Similarity-Preserving Knowledge Distillation
- Expectation-Maximization Attention Networks for Semantic Segmentation
- Orientation-aware Semantic Segmentation on Icosahedron Spheres
- Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking
- Learning Lightweight Lane Detection CNNs by Self Attention Distillation [code]
- arXiv
- Consensus Feature Network for Scene Parsing
- Deep Co-Training for Semi-Supervised Image Segmentation
- Residual Pyramid Learning for Single-Shot Semantic Segmentation
- What Synthesis is Missing: Depth Adaptation Integrated with Weak Supervision for Indoor Scene Parsing
- Dynamic Deep Networks for Retinal Vessel Segmentation
- Efficient Smoothing of Dilated Convolutions for Image Segmentation
- Adaptive Masked Weight Imprinting for Few-Shot Segmentation
- An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions
- Lift-the-Flap: Context Reasoning Using Object-Centered Graphs
- Fast-SCNN: Fast Semantic Segmentation Network
- THE EFFECT OF SCENE CONTEXT ON WEAKLY SUPERVISED SEMANTIC SEGMENTATION
- MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation
- On Boosting Semantic Street Scene Segmentation with Weak Supervision
2018
-
CVPR 2018
- Compassionately Conservative Balanced Cuts for Image Segmentation
- icient interactive annotation of segmentation datasets with polygon rnn++ [code]
- Guided Proofreading of Automatic Segmentations for Connectomics
- DenseASPP for Semantic Segmentation in StreetScenes
- Context Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation
- Recurrent Scene Parsing with Perspective Understanding in the Loop
- PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing
- Learning a Discriminative Feature Network for Semantic Segmentation
- Context Encoding for Semantic Segmentation
- Dynamic-structured Semantic Propagation Network
- In-Place Activated BatchNorm for Memory-Optimized Training of DNNs
- Error Correction for Dense Semantic Image Labeling
- Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation
- Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation
- On the Importance of Label Quality for Semantic Segmentation
- Referring Image Segmentation via Recurrent Refinement Networks [From NLP] [code]
- Learning Superpixels with Segmentation-Aware Affinity Loss [Superpixel seg]
- Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer [Human Part Seg] [code]
- Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning [WSL]
- Learning Pixel-Level Semantic Affinity With Image-Level Supervision for Weakly Supervised Semantic Segmentation [WSL]
- Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region Growing [WSL]
- Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation [WSL]
- Bootstrapping the Performance of Webly Supervised Semantic Segmentation [WSL]
- Normalized Cut Loss for Weakly-Supervised CNN Segmentation [WSL]
- Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features [WSL]
- Weakly Supervised Instance Segmentation Using Class Peak Response [WSL]
-
ECCV 2018
- Multi-Scale Context Intertwining for Semantic Segmentation
- Unified Perceptual Parsing for Scene Understanding
- ExFuse: Enhancing Feature Fusion for Semantic Segmentation
- BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
- ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
- PSANet: Point-wise Spatial Attention Network for Scene Parsing
- ICNet for Real-Time Semantic Segmentation on High-Resolution Images
- Adaptive Affinity Fields for Semantic Segmentation
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
-
Other 18'conferences
- RelationNet: Learning Deep-Aligned Representation for Semantic Image Segmentation [ICPR]
- High Resolution Feature Recovering for Accelerating Urban Scene Parsing [IJCAI]
- Mix-and-Match Tuning for Self-Supervised Semantic Segmentation [AAAI]
- Spatial As Deep: Spatial CNN for Traffic Scene Understanding Xingang [AAAI]
- A Probabilistic U-Net for Segmentation of Ambiguous Images [NIPS]
- DifNet: Semantic Segmentation by Diffusion Networks [NIPS]
- Beyond Grids: Learning Graph Representations for Visual Recognition [NIPS] [GCN]
- Symbolic Graph Reasoning Meets Convolutions [NIPS] [GCN]
- A^2-Nets: Double Attention Networks [NIPS] [GCN]
- Searching for Efficient Multi-Scale Architectures for Dense Image Prediction [NIPS] [NAS]
-
ArXiv
- Improving Semantic Segmentation via Video Propagation and Label Relaxation
- Evaluating Bayesian Deep Learning Methods for Semantic Segmentation
- ShelfNet for Real-time Semantic Segmentation, Multi-path segmentation network
- CCNet: Criss-Cross Attention for Semantic Segmentation
- Dual Attention Network for Scene Segmentation
- Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation
- Locally Adaptive Learning Loss for Semantic Image Segmentation
- RTSEG: REAL-TIME SEMANTIC SEGMENTATION COMPARATIVE STUDY
- OCNet: Object Context Network for Scene Parsing
- CGNet: A Light-weight Context Guided Network for Semantic Segmentation
2017
-
CVPR 2017
- Convolutional RandomWalk Networks for Semantic Image Segmentation
- Dilated Residual Networks
- Learning Adaptive Receptive Fields for Deep Image Parsing Network
- Loss Max-Pooling for Semantic Image Segmentation
- Semantic Segmentation via Structured Patch Prediction, Context CRF and Guidance CRF
- Pyramid Scene Parsing Network
- Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
- Refinenet: Multi-path refinement networks for high-resolution semantic segmentation
- Gated Feedback Refinement Network for Dense Image Labeling
-
ICCV 2017
- Deep Dual Learning for Semantic Image Segmentation
- Semi Supervised Semantic Segmentation Using Generative Adversarial Network
- Scale-adaptive Convolutions for Scene Parsing
- Predicting Deeper into the Future of Semantic Segmentation
- Segmentation-Aware Convolutional Networks Using Local Attention Mask
- Dense and Low-Rank Gaussian CRFs Using Deep Embeddings Siddhartha
- FoveaNet: Perspective-aware Urban Scene Parsing
-
Other 17'conferences
- Understanding Convolution for Semantic Segmentation[WACV]
- Learning Affinity via Spatial Propagation Networks[NIPS]
- Dual Path Networks[NIPS]
- Semantic Segmentation with Reverse Attention[BMVC]
- The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation[CVPRW]
- Fully Convolutional Networks for Semantic Segmentation [TPAMI]
-
ArXiv
2016
-
CVPR 2016
-
ECCV 2016
-
Other 16'conferences
- Semantic Segmentation using Adversarial Networks [NIPSW]
- Speeding up Semantic Segmentation for Autonomous Driving [NIPSW]
- ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation [PyTorch]
- Multi-Scale Context Aggregation by Dilated Convolutions [ICLR] [PyTorch]
- Learning Dense Convolutional Embeddings for Semantic Segmentation[ICLR]
-
ArXiv
2015
-
CVPR 2015
- Fully Convolutional Networks for Semantic Segmentation
- Hypercolumns for Object Segmentation and Fine-grained Localization
- Weakly supervised semantic segmentation for social images
- Scene Labeling with LSTM Recurrent Neural Networks
- Learning to Propose Objects [PyTorch] [Project]
- Feedforward semantic segmentation with zoom-out features
-
ICCV 2015
-
Other 15'conferences
-
ArXiv
Before 2015
- Simultaneous Detection and Segmentation [ECCV2014]
- Nonparametric Scene Parsing via Label Transfer [TPAMI2011][Project]
- Dense Segmentation-aware Descriptors[CVPR2013]
- Semantic Segmentation with Second-Order Pooling [ECCV2012]
Repos
- https://github.com/ZijunDeng/pytorch-semantic-segmentation [PyTorch]
- https://github.com/meetshah1995/pytorch-semseg [PyTorch]
Instance Segmentation
- Learning to Segment Object Candidates
- Recurrent Instance Segmentation [ECCV2016]
- Instance-aware Semantic Segmentation via Multi-task Network Cascades
- Learning to Refine Object Segments
- Fully Convolutional Instance-aware Semantic Segmentation
- Mask R-CNN
Panoptic Segmentation
- Panoptic Segmentation
- Single Network Panoptic Segmentation for Street Scene Understanding
- DeeperLab: Single-Shot Image Parser
- An End-to-End Network for Panoptic Segmentation
Video Segmentation
2018
-
CVPR 2018
- Actor and Action Video Segmentation from a Sentence [project]
- Dynamic Video Segmentation Network
- Semantic Video Segmentation by Gated Recurrent Flow Propagation
- Deep Spatio-Temporal Random Fields for Efficient Video Segmentation [code]
- Low-Latency Video Semantic Segmentation
- CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF
- Efficient Video Object Segmentation via Network Modulation [code]
- Instance Embedding Transfer to Unsupervised Video Object Segmentation
- Fast Video Object Segmentation by Reference-Guided Mask Propagation [code]
- Fast and Accurate Online Video Object Segmentation via Tracking Parts [code]
- Reinforcement Cutting-Agent Learning for Video Object Segmentation
- Blazingly Fast Video Object Segmentation With Pixel-Wise Metric Learning
- MoNet: Deep Motion Exploitation for Video Object Segmentation
- Motion-Guided Cascaded Refinement Network for Video Object Segmentation
-
others
Saliency Detection
- Contextual Encoder-Decoder Network for Visual Saliency Prediction
- Understanding and Visualizing Deep Visual Saliency Models (CVPR2019)
- SAC-Net: Spatial Attenuation Context for Salient Object Detectio
RNN
Graphical Models (CRF, MRF)
- https://github.com/cvlab-epfl/densecrf
- http://vladlen.info/publications/efficient-inference-in-fully-connected-crfs-with-gaussian-edge-potentials/
- http://www.philkr.net/home/densecrf
- http://graphics.stanford.edu/projects/densecrf/
- https://github.com/amiltonwong/segmentation/blob/master/segmentation.ipynb
- https://github.com/jliemansifry/super-simple-semantic-segmentation
- http://users.cecs.anu.edu.au/~jdomke/JGMT/
- https://www.quora.com/How-can-one-train-and-test-conditional-random-field-CRF-in-Python-on-our-own-training-testing-dataset
- https://github.com/tpeng/python-crfsuite
- https://github.com/chokkan/crfsuite
- https://sites.google.com/site/zeppethefake/semantic-segmentation-crf-baseline
- https://github.com/lucasb-eyer/pydensecrf
Datasets:
- Stanford Background Dataset
- Sift Flow Dataset
- Barcelona Dataset
- Microsoft COCO dataset
- MSRC Dataset
- LITS Liver Tumor Segmentation Dataset
- KITTI
- Pascal Context
- Data from Games dataset
- Human parsing dataset
- Mapillary Vistas Dataset
- Microsoft AirSim
- MIT Scene Parsing Benchmark
- COCO 2017 Stuff Segmentation Challenge
- ADE20K Dataset
- INRIA Annotations for Graz-02
- Daimler dataset
- ISBI Challenge: Segmentation of neuronal structures in EM stacks
- INRIA Annotations for Graz-02 (IG02)
- Pratheepan Dataset
- Clothing Co-Parsing (CCP) Dataset
- Inria Aerial Image
other papers
- Ranked List Loss for Deep Metric Learning [CVPR2019]
- Video Generation from Single Semantic Label Map [CVPR2019]
- Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation [CVPR2019]
- Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation
- Group-wise Correlation Stereo Network [CVPR2019]
- Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks [CVPR2019]
- Similarity Learning via Kernel Preserving Embedding [AAAI2019]
- Unsupervised Person Re-identification by Soft Multilabel Learning [CVPR2019]
- Learning Robust Representations by Projecting Superficial Statistics Out [ICLR2019]
- MFAS: Multimodal Fusion Architecture Search [CVPR2019]
- SimulCap : Single-View Human Performance Capture with Cloth Simulation [CVPR2019]
- Semantic Image Synthesis with Spatially-Adaptive Normalization [CVPR2019]
- Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection [CVPR2019]
- QATM: Quality-Aware Template Matching For Deep Learning [CVPR2019]
- AdaGraph: Unifying Predictive and Continuous Domain Adaptation through Graphs [CVPR2019]
- Selective Kernel Networks [CVPR2019]
- Towards Robust Curve Text Detection with Conditional Spatial Expansion [CVPR2019]
- Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation [CVPR2019]
- Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration [CVPR2019]
- Networks for Joint Affine and Non-parametric Image Registration [CVPR2019]
- OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations [CVPR2019]
- Semantic Alignment: Finding Semantically Consistent Ground-truth for Facial Landmark Detection [CVPR2019]
- Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation [CVPR2019]
- f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning [CVPR2019]
- Residual Non-local Attention Networks for Image Restoration [ICLR2019]
- Self-Supervised Learning via Conditional Motion Propagation [CVPR2019]
Blog posts, other:
- https://handong1587.github.io/deep_learning/2015/10/09/segmentation.html
- http://www.andrewjanowczyk.com/efficient-pixel-wise-deep-learning-on-large-images/
- https://devblogs.nvidia.com/parallelforall/image-segmentation-using-digits-5/
- https://github.com/NVIDIA/DIGITS/tree/master/examples/binary-segmentation
- https://github.com/NVIDIA/DIGITS/tree/master/examples/semantic-segmentation