Context For Semantic Segmentation Gang Yu 旷 视 研 究 院
Collaborators Changqian Yu Jingbo Wang Chao Peng Xiangyu Zhang Changxin Gao Nong Sang Gang Yu Jian Sun
Outline • Revisit Semantic Segmentation • Context for Semantic Segmentation • Backbone • Head • Loss • Conclusion
Outline • Revisit Semantic Segmentation • Context for Semantic Segmentation • Backbone • Head • Loss • Conclusion
What is Semantic Segmentation? • Classification + Localization • Visual Recognition • Classification • Semantic Segmentation • Instance Segmentation • Panoptic Segmentation • Detection • Keypoint Detection
Pipeline Softmax LOSS L2 … Backbone Head U-Shape VGG16 4/8-Sampling + Dilation ResNet … ResNext …
Challenges in Semantic Segmentation? • Speed • Performance • Per-pixel Accuracy • Boundary
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
Outline • Revisit Semantic Segmentation • Context for Semantic Segmentation • Backbone • Head • Loss • Conclusion
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?
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
Context in Loss • Motivation • “Thing” may be important for stuff prediction COCO2018 Panoptic Segmentation Challenge, http://presentations.cocodataset.org/ECCV18/COCO18-Panoptic-Megvii.pdf
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