context for semantic segmentation
play

Context For Semantic Segmentation Gang Yu Collaborators - PowerPoint PPT Presentation

Context For Semantic Segmentation Gang Yu Collaborators Changqian Yu Jingbo Wang Chao Peng Xiangyu Zhang Changxin Gao Nong Sang Gang Yu Jian Sun Outline Revisit Semantic Segmentation Context for Semantic


  1. Context For Semantic Segmentation Gang Yu 旷 视 研 究 院

  2. Collaborators Changqian Yu Jingbo Wang Chao Peng Xiangyu Zhang Changxin Gao Nong Sang Gang Yu Jian Sun

  3. Outline • Revisit Semantic Segmentation • Context for Semantic Segmentation • Backbone • Head • Loss • Conclusion

  4. Outline • Revisit Semantic Segmentation • Context for Semantic Segmentation • Backbone • Head • Loss • Conclusion

  5. What is Semantic Segmentation? • Classification + Localization • Visual Recognition • Classification • Semantic Segmentation • Instance Segmentation • Panoptic Segmentation • Detection • Keypoint Detection

  6. Pipeline Softmax LOSS L2 … Backbone Head U-Shape VGG16 4/8-Sampling + Dilation ResNet … ResNext …

  7. Challenges in Semantic Segmentation? • Speed • Performance • Per-pixel Accuracy • Boundary

  8. What is Context? • According to Dictionary: • the parts of a discourse that surround a word or passage and can throw light on its meaning Grass Person Play Fields Sports ball

  9. Outline • Revisit Semantic Segmentation • Context for Semantic Segmentation • Backbone • Head • Loss • Conclusion

  10. Context in Backbone • Motivation • Traditional Backbone is designed for Classification • Large Receptive field by compromising spatial resolution • Segmentation requires both Classification & Localization • Maintain both Receptive Field (context) & Spatial resolution • Computational cost?

  11. Context in Backbone - BiSeNet • BiSeNet: Bilateral Segmentation Network BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation, Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang, ECCV, 2018

  12. Context in Backbone - BiSeNet • Pipeline BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation, Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang, ECCV, 2018

  13. Context in Backbone - BiSeNet • Results BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation, Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang, ECCV, 2018

  14. Context in Backbone - BiSeNet • Ablation Results BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation, Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang, ECCV, 2018

  15. Context in Backbone - BiSeNet • Speed BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation, Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang, ECCV, 2018

  16. Context in Backbone - BiSeNet • Summary • Two path in backbone: Spatial path + Context path • Context is implicitly encoded in receptive field • Efficient speed • Code: https://github.com/ycszen/TorchSeg • Context: • A branch encodes semantic meaning with large receptive field? • Related work: • ICNet for Real-Time Semantic Segmentation on High-Resolution Images, Hengshuang Zhao, Xiaojuan Qi, Xiaoyong Shen, Jianping Shi, Jiaya Jia, ECCV2018 • Stacked Hourglass Networks for Human Pose Estimation, Alejandro Newell, Kaiyu Yang, Jia Deng, ECCV2016 BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation, Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang, ECCV, 2018

  17. Context in Head • Motivation • Large Receptive field without compromising boundary results • Why working on Head? • Efficient speed • Obvious gain on increasing the receptive • Simple to implement

  18. Context in Head – Large Kernel • Receptive Field vs Valid Receptive Field Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network, Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, Jian Sun, CVPR, 2017

  19. Context in Head – Large Kernel • Large Kernel Matters Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network, Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, Jian Sun, CVPR, 2017

  20. Context in Head – Large Kernel • Large Kernel Matters • Why Boundary Refinement? • Large receptive field will blur the object boundary Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network, Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, Jian Sun, CVPR, 2017

  21. Context in Head – Large Kernel • Large Kernel Matters • Ablation: Why Boundary Refinement? • Large receptive field will blur the object boundary Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network, Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, Jian Sun, CVPR, 2017

  22. Context in Head – Large Kernel • Large Kernel Matters • Ablation: Different kernel size? Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network, Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, Jian Sun, CVPR, 2017

  23. Context in Head – Large Kernel • Large Kernel Matters • Ablation: Are more parameters helpful? Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network, Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, Jian Sun, CVPR, 2017

  24. Context in Head – Large Kernel • Large Kernel Matters • Ablation: GCN vs. Stack of small convolutions Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network, Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, Jian Sun, CVPR, 2017

  25. Context in Head – Large Kernel • Large Kernel Matters • Ablation: GCN in Backbone Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network, Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, Jian Sun, CVPR, 2017

  26. Context in Head – Large Kernel • Large Kernel Matters: illustrative examples Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network, Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, Jian Sun, CVPR, 2017

  27. Context in Head – Large Kernel • Summary • Global Convolution network to increase the receptive field • Large separable convolution is an efficient implementation • Context • Large receptive field? • Related work • PSPNet: Pyramid Scene Parsing Network, Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia, CVPR2017 • DeeplabV3: Rethinking Atrous Convolution for Semantic Image Segmentation, Liang-Chieh Chen, George Papandreou, Florian Schroff, Hartwig Adam Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network, Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, Jian Sun, CVPR, 2017

  28. Context in Head – DFN • Motivation: • Large kernel (GCN) is computationally intensive • Global pooling is efficient to compute and can obtain the global context • Large receptive field does not equal to good context • Attention strategy to adaptively aggreate the features Learning a Discriminative Feature Network for Semantic Segmentation, Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang, CVPR, 2018

  29. Context in Head – DFN • DFN: Pipeline Learning a Discriminative Feature Network for Semantic Segmentation, Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang, CVPR, 2018

  30. Context in Head – DFN • DFN: Ablation Learning a Discriminative Feature Network for Semantic Segmentation, Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang, CVPR, 2018

  31. Context in Head – DFN • DFN: Results Learning a Discriminative Feature Network for Semantic Segmentation, Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang, CVPR, 2018

  32. Context in Head – DFN • Summary • Global pooling is efficient and effective to capture the long-range context • Attention for adaptive adjusting feature weights • Code: https://github.com/ycszen/TorchSeg/ • Context • Receptive field & feature aggregation? • Related work • Non-local Neural Networks, Xiaolong Wang, Ross Girshick, Abhinav Gupta, Kaiming He, CVPR2018 • CCNet: Criss-Cross Attention for Semantic Segmentation, Zilong Huang, Xinggang Wang, Lichao Huang, Chang Huang, Yunchao Wei, Wenyu Liu • PSANet: Point-wise Spatial Attention Network for Scene Parsing, Hengshuang Zhao*, Yi Zhang*, Shu Liu, Jianping Shi, Chen Change Loy, Dahua Lin, Jiaya Jia, ECCV2018 • OCNet: Object Context Network for Scene Parsing, Yuhui Yuan, Jingdong Wang • ParseNet: Looking Wider to See Better, Wei Liu, Andrew Rabinovich, Alexander C. Berg Learning a Discriminative Feature Network for Semantic Segmentation, Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang, CVPR, 2018

  33. Context in Loss • Motivation • “Thing” may be important for stuff prediction Grass Person Play Fields Sports ball COCO2018 Panoptic Segmentation Challenge, http://presentations.cocodataset.org/ECCV18/COCO18-Panoptic-Megvii.pdf

  34. Context in Loss • Motivation • “Thing” may be important for stuff prediction COCO2018 Panoptic Segmentation Challenge, http://presentations.cocodataset.org/ECCV18/COCO18-Panoptic-Megvii.pdf

  35. Context in Loss • Pipeline Objects Semantic Stuff Stuff Multi Types Context Train/Inference Train Supervision Res-Block Encoder Inference Merge COCO2018 Panoptic Segmentation Challenge, http://presentations.cocodataset.org/ECCV18/COCO18-Panoptic-Megvii.pdf

Recommend


More recommend