图像分割：汇总

本文系转载，版权归原作者所有。原文链接：http://www.aiuai.cn/aifarm62.html

1. Semantic Segmentation

1. FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference - CVPR2019 <Paper>
2. An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions - 2019 <Paper>
3. Fast-SCNN: Fast Semantic Segmentation Network - 2019 <Paper>
4. Data augmentation using learned transforms for one-shot medical image segmentation - CVPR2019 <Paper>
5. MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation - 2019 <Paper>
6. CCNet: Criss-Cross Attention for Semantic Segmentation - 2018 <Paper> <Code-PyTorch>
7. A PyTorch Semantic Segmentation Toolbox - 2018 <Paper> <Code-PyTorch>
8. ShelfNet for Real-time Semantic Segmentation - 2018 <Paper> <Code-PyTorch>
9. Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training - ECCV2018 <Paper> <Project> <Code-MXNet>
10. Searching for Efficient Multi-Scale Architectures for Dense Image Prediction - 2018 - Deeplab <Paper><Code-Deeplab-Tensorflow>
11. Light-Weight RefineNet for Real-Time Semantic Segmentation - bmvc2018 <Paper> <Code-Torch>
12. Dual Attention Network for Scene Segmentation - 2018 <Paper>
13. BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation - ECCV 2018 - Face++ <Paper>
14. Adaptive Affinity Field for Semantic Segmentation - ECCV2018 <Paper> <HomePage>
15. Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation - CVPR2018 <Paper>
16. DenseASPP for Semantic Segmentation in Street Scenes - CVPR2018 <Paper> <Code-PyTorch>
17. Pyramid Attention Network for Semantic Segmentation - 2018 - Face++ <Paper>
18. Autofocus Layer for Semantic Segmentation - 2018 <Paper <Code-PyTorch>
19. ExFuse: Enhancing Feature Fusion for Semantic Segmentation - ECCV2018 - Face++ <Paper>
20. DifNet: Semantic Segmentation by Diffusion Networks - 2018 <Paper>
21. Convolutional CRFs for Semantic Segmentation - 2018 <Paper><Code-PyTorch>
22. ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time - 2018 <Paper>
23. Learning a Discriminative Feature Network for Semantic Segmentation - CVPR2018 - Face++ <Paper>
24. Vortex Pooling: Improving Context Representation in Semantic Segmentation - 2018 <Paper>
25. Fully Convolutional Adaptation Networks for Semantic Segmentation - CVPR2018 <Paper>
26. A Multi-Layer Approach to Superpixel-based Higher-order Conditional Random Field for Semantic Image Segmentation - 2018 <Paper>
27. Context Encoding for Semantic Segmentation - 2018 <Paper> <Code-PyTorch> <Code-PyTorch2> <Slides>
28. ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation - ECCV2018 <Paper> <Code-Pytorch>
29. Dynamic-structured Semantic Propagation Network - 2018 - CMU <Paper>
30. ShuffleSeg: Real-time Semantic Segmentation Network-2018 <Paper> <Code-TensorFlow>
31. RTSeg: Real-time Semantic Segmentation Comparative Study - 2018 <Paper> <Code-TensorFlow>
32. Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation - 2018 <Paper>
33. DeepLabV3+:Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation - 2018 - Google <Paper> <Code-Tensorflow> <Code-Karas>
34. Adversarial Learning for Semi-Supervised Semantic Segmentation - 2018 <Paper> <Code-PyTorch>
35. Locally Adaptive Learning Loss for Semantic Image Segmentation - 2018 <Paper>
36. Learning to Adapt Structured Output Space for Semantic Segmentation - 2018 <Paper>
37. Improved Image Segmentation via Cost Minimization of Multiple Hypotheses - 2018 <Paper> <Code-Matlab>
38. TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation - 2018 - Kaggle <Paper> <Code-PyTorch> <Kaggle-Carvana Image Masking Challenge>
39. Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation - 2018 - Google <Paper>
40. End-to-end Detection-Segmentation Network With ROI Convolution - 2018 <Paper>
41. Mix-and-Match Tuning for Self-Supervised Semantic Segmentation - AAAI2018 <Project> <Paper> <Code-Caffe>
42. Learning to Segment Every Thing-2017 <Paper> <Code-Caffe2> <Code-PyTorch>
43. Deep Dual Learning for Semantic Image Segmentation-2017 <Paper>
44. Scene Parsing with Global Context Embedding - ICCV2017 <Paper>
45. FoveaNet: Perspective-aware Urban Scene Parsing - ICCV2017 <Paper>
46. Segmentation-Aware Convolutional Networks Using Local Attention Masks - 2017 <Paper> <Code-Caffe> <Project>
47. Stacked Deconvolutional Network for Semantic Segmentation-2017 <Paper>
48. Semantic Segmentation via Structured Patch Prediction, Context CRF and Guidance CRF - CVPR2017 <Paper> <Caffe-Code>
49. BlitzNet: A Real-Time Deep Network for Scene Understanding-2017 <Project> <Code-Tensorflow> <Paper>
50. Efficient Yet Deep Convolutional Neural Networks for Semantic Segmentation -2017 <Paper> <Code-Caffe>
51. LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation - 2017 <Paper> <Code-Torch>
52. Rethinking Atrous Convolution for Semantic Image Segmentation-2017(DeeplabV3) <Paper>
53. Learning Object Interactions and Descriptions for Semantic Image Segmentation-2017 <Paper>
54. Pixel Deconvolutional Networks-2017 <Code-Tensorflow> <Paper>
55. Dilated Residual Networks-2017 <Paper> <Code-PyTorch>
56. Recurrent Scene Parsing with Perspective Understanding in the Loop - 2017 <Project> <Paper> <Code-MatConvNet>
57. A Review on Deep Learning Techniques Applied to Semantic Segmentation-2017 <Paper>
58. BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks <Paper>
59. Efficient ConvNet for Real-time Semantic Segmentation - 2017 <Paper>
60. ICNet for Real-Time Semantic Segmentation on High-Resolution Images-2017 <Project> <Code-Caffe><Paper> <Video>
61. Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade-2017 <Paper> <Poster> <Project> <Code-Caffe> <Slides>
62. Loss Max-Pooling for Semantic Image Segmentation-2017 <Paper>
63. Annotating Object Instances with a Polygon-RNN-2017 <Project> <Paper>
64. Feature Forwarding: Exploiting Encoder Representations for Efficient Semantic Segmentation-2017 <Project> <Code-Torch7>
65. Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation-2017 <Paper>
66. Adversarial Examples for Semantic Image Segmentation-2017 <Paper>
67. Large Kernel Matters - Improve Semantic Segmentation by Global Convolutional Network-2017 <Paper>
68. Label Refinement Network for Coarse-to-Fine Semantic Segmentation-2017 <Paper>
69. PixelNet: Representation of the pixels, by the pixels, and for the pixels-2017 <Project> <Code-Caffe> <Paper>
70. LabelBank: Revisiting Global Perspectives for Semantic Segmentation-2017 <Paper>
71. Progressively Diffused Networks for Semantic Image Segmentation-2017 <Paper>
72. Understanding Convolution for Semantic Segmentation-2017 <Model-Mxnet> <Mxnet-Code> <Paper>
73. Predicting Deeper into the Future of Semantic Segmentation-2017 <Paper>
74. Pyramid Scene Parsing Network-2017 <Project> <Code-Caffe> <Paper> <Slides>
75. FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation-2016 <Paper>
76. FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics-2016 <Code-PyTorch> <Paper>
77. RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation-2016 <Code-MatConvNet> <Paper> <Code-Pytorch>
78. Learning from Weak and Noisy Labels for Semantic Segmentation - 2017 <Paper>
79. The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation <Code-Theano> <Code-Keras1> <Code-Keras2> <Paper>
80. Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes <Code-Theano> <Paper>
81. PixelNet: Towards a General Pixel-level Architecture-2016 <Paper>
82. Recalling Holistic Information for Semantic Segmentation-2016 <Paper>
83. Semantic Segmentation using Adversarial Networks-2016 <Paper> <Code-Chainer>
84. Region-based semantic segmentation with end-to-end training-2016 <Paper>
85. Exploring Context with Deep Structured models for Semantic Segmentation-2016 <Paper>
86. Better Image Segmentation by Exploiting Dense Semantic Predictions-2016 <Paper>
87. Boundary-aware Instance Segmentation-2016 <Paper>
88. Improving Fully Convolution Network for Semantic Segmentation-2016 <Paper>
89. Deep Structured Features for Semantic Segmentation-2016 <Paper>
90. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs-2016 <Project> <Code-Caffe> <Code-Tensorflow> <Code-PyTorch> <Paper>
91. DeepLab: Semantic Image Segmentation With Deep Convolutional Nets and Fully Connected CRFs-2014 <Code-Caffe1> <Code-Caffe2> <Paper>
92. Deep Learning Markov Random Field for Semantic Segmentation-2016 <Project> <Paper>
93. Convolutional Random Walk Networks for Semantic Image Segmentation-2016 <Paper>
94. ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation-2016 <Code-Caffe1><Code-Caffe2> <Paper> <Blog>
95. High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks-2016 <Paper>
96. ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation-2016 <Paper>
97. Object Boundary Guided Semantic Segmentation-2016 <Code-Caffe> <Paper>
98. Segmentation from Natural Language Expressions-2016 <Project> <Code-Tensorflow> <Code-Caffe><Paper>
99. Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation-2016 <Code-Caffe> <Paper>
100. Global Deconvolutional Networks for Semantic Segmentation-2016 <Paper> <Code-Caffe>
101. Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network-2015 <Project> <Code-Caffe> <Paper>
102. Learning Dense Convolutional Embeddings for Semantic Segmentation-2015 <Paper>
103. ParseNet: Looking Wider to See Better-2015 <Code-Caffe> <Model-Caffe> <Paper>
104. Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation-2015 <Project> <Code-Caffe> <Paper>
105. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation-2015 <Project> <Code-Caffe> <Paper> <Tutorial1> <Tutorial2>
106. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling-2015 <Code-Caffe> <Code-Chainer> <Paper>
107. Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform-2015 <Paper>
108. Semantic Segmentation with Boundary Neural Fields-2015 <Code-Matlab> <Paper>
109. Semantic Image Segmentation via Deep Parsing Network-2015 <Project> <Paper1> <Paper2> <Slides>
110. What’s the Point: Semantic Segmentation with Point Supervision-2015 <Project> <Code-Caffe> <Model-Caffe> <Paper>
111. U-Net: Convolutional Networks for Biomedical Image Segmentation-2015 <Project> <Code+Data> <Code-Keras> <Code-Tensorflow> <Paper> <Notes>
112. Learning Deconvolution Network for Semantic Segmentation(DeconvNet)-2015 <Project> <Code-Caffe> <Paper> <Slides>
113. Multi-scale Context Aggregation by Dilated Convolutions-2015 <Project> <Code-Caffe> <Code-Keras><Paper> <Notes>
114. ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation-2015 <Code-Theano> <Paper>
115. BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation-2015 <Paper>
116. Feedforward semantic segmentation with zoom-out features-2015 <Code-Torch> <Paper> <Video>
117. Conditional Random Fields as Recurrent Neural Networks-2015 <Project> <Code-Caffe1> <Code-Caffe2> <Demo> <Paper1> <Paper2>
118. Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation-2015 <Paper>
119. Fully Convolutional Networks for Semantic Segmentation-2015 <Code-Caffe> <Model-Caffe> <Code-Tensorflow1> <Code-Tensorflow2> <Code-Chainer> <Code-PyTorch> <Paper1> <Paper2> <Slides1> <Slides2>
120. Deep Joint Task Learning for Generic Object Extraction-2014 <Project> <Code-Caffe> <Dataset> <Paper>
121. Highly Efficient Forward and Backward Propagation of Convolutional Neural Networks for Pixelwise Classification-2014 <Code-Caffe> <Paper>

2. Panoptic Segmentation

1. UPSNet: A Unified Panoptic Segmentation Network - 2019 <Paper>
2. An End-to-end Network for Panoptic Segmentation - Face++ - CVPR2019 [<Paper>]()
3. Attention-guided Unified Network for Panoptic Segmentation - CVPR2019 <Paper>
4. Single Network Panoptic Segmentation for Street Scene Understanding - 2019 <Paper>
5. Panoptic Feature Pyramid Networks - 2019 <Paper>
6. DeeperLab: Single-Shot Image Parser - 2019 <Paper>
7. Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network - 2019 <Paper>
8. Weakly- and Semi-Supervised Panoptic Segmentation - ECCV2018 <Paper> <Code-Matlab> <Project><Poster>
9. Panoptic Segmentation - 2018 <Paper>

3. Human Parsing

1. Macro-Micro Adversarial Network for Human Parsing - ECCV2018 <Paper> <Code-PyTorch>
2. Holistic, Instance-level Human Parsing - 2017 <Paper>
3. Semi-Supervised Hierarchical Semantic Object Parsing - 2017 <Paper>
4. Towards Real World Human Parsing: Multiple-Human Parsing in the Wild - 2017 <Paper>
5. Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing-2017 <Project> <Code-Caffe> <Paper>
6. Efficient and Robust Deep Networks for Semantic Segmentation - 2017 <Paper> <Project> <Code-Caffe>
7. Deep Learning for Human Part Discovery in Images-2016 <Code-Chainer> <Paper>
8. A CNN Cascade for Landmark Guided Semantic Part Segmentation-2016 <Project> <Paper>
9. Deep Learning for Semantic Part Segmentation With High-level Guidance-2015 <Paper>
10. Neural Activation Constellations-Unsupervised Part Model Discovery with Convolutional Networks-2015<Paper>
11. Human Parsing with Contextualized Convolutional Neural Network-2015 <Paper>
12. Part detector discovery in deep convolutional neural networks-2014 <Code-Matlab> <Paper>

4. Clothes Parsing

1. Looking at Outfit to Parse Clothing-2017 <Paper>
2. Semantic Object Parsing with Local-Global Long Short-Term Memory-2015 <Paper>
3. A High Performance CRF Model for Clothes Parsing-2014 <Project> <Code-Matlab> <Dataset> <Paper>
4. Clothing co-parsing by joint image segmentation and labeling-2013 <Project> <Dataset> <Paper>
5. Parsing clothing in fashion photographs-2012 <Project> <Paper>

5. Instance Segmentation

1. A Pyramid CNN for Dense-Leaves Segmentation - 2018 <Paper>
2. Predicting Future Instance Segmentations by Forecasting Convolutional Features - 2018 <Paper>
3. Path Aggregation Network for Instance Segmentation - CVPR2018 <Paper> <Code-PyTorch>
4. PixelLink: Detecting Scene Text via Instance Segmentation - AAAI2018 <Code-Tensorflow> <Paper>
5. MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features - 2017 - google <Paper>
6. Recurrent Neural Networks for Semantic Instance Segmentation-2017 <Paper>
7. Pixelwise Instance Segmentation with a Dynamically Instantiated Network-2017 <Paper>
8. Semantic Instance Segmentation via Deep Metric Learning-2017 <Paper>
9. Mask R-CNN-2017 <Code-Tensorflow> <Paper> <Code-Caffe2> <Code-Karas> <Code-PyTorch> <Code-MXNet>
10. Pose2Instance: Harnessing Keypoints for Person Instance Segmentation-2017 <Paper>
11. Pixelwise Instance Segmentation with a Dynamically Instantiated Network-2017 <Paper>
12. Semantic Instance Segmentation with a Discriminative Loss Function-2017 <Paper>
13. Fully Convolutional Instance-aware Semantic Segmentation-2016 <Code-MXNet> <Paper>
14. End-to-End Instance Segmentation with Recurrent Attention <Paper> <Code-Tensorflow>
15. Instance-aware Semantic Segmentation via Multi-task Network Cascades-2015 <Code-Caffe> <Paper>
16. Recurrent Instance Segmentation-2015 <Project> <Code-Torch7> <Paper> <Poster> <Video>

6. Segment Object Candidates

1. Contextual Encoder-Decoder Network for Visual Saliency Prediction - 2019 <Paper>
2. FastMask: Segment Object Multi-scale Candidates in One Shot-2016 <Code-Caffe> <Paper>
3. Learning to Refine Object Segments-2016 <Code-Torch> <Paper>
4. Learning to Segment Object Candidates-2015 <Code-Torch> <Code-Theano-Keras> <Paper>

7. Foreground Object Segmentation

1. Pixel Objectness-2017 <Project> <Code-Caffe> <Paper>
2. A Deep Convolutional Neural Network for Background Subtraction-2017 <Paper>