CSCL: Critical Semantic-Consistent Learning for Unsupervised Domain Adaptation

Unsupervised domain adaptation without consuming annotation process for unlabeled target data attracts appealing interests in semantic segmentation. However, 1) existing methods neglect that not all semantic representations across domains are transferable, which cripples domain-wise transfer with untransferable knowledge; 2) they fail to narrow category-wise distribution shift due to category-agnostic feature alignment. To address above challenges, we develop a new Critical Semantic-Consistent Learning (CSCL) model, which mitigates the discrepancy of both domain-wise and category-wise distributions. Specifically, a critical transfer based adversarial framework is designed to highlight transferable domain-wise knowledge while neglecting untransferable knowledge. Transferability-critic guides transferability-quantizer to maximize positive transfer gain under reinforcement learning manner, although negative transfer of untransferable knowledge occurs. Meanwhile, with the help of confidence-guided pseudo labels generator of target samples, a symmetric soft divergence loss is presented to explore inter-class relationships and facilitate category-wise distribution alignment. Experiments on several datasets demonstrate the superiority of our model.

[1]  Yandong Tang,et al.  Laplacian pyramid adversarial network for face completion , 2019, Pattern Recognit..

[2]  Nicolas Courty,et al.  Joint distribution optimal transportation for domain adaptation , 2017, NIPS.

[3]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Yang Zou,et al.  Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training , 2018, ArXiv.

[5]  Qianqian Wang,et al.  Visual Tactile Fusion Object Clustering , 2020, AAAI.

[6]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[7]  Jingang Tan,et al.  SSF-DAN: Separated Semantic Feature Based Domain Adaptation Network for Semantic Segmentation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[8]  Ming Yang,et al.  Conditional Generative Adversarial Network for Structured Domain Adaptation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  Iasonas Kokkinos,et al.  Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs , 2014, ICLR.

[10]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Nuno Vasconcelos,et al.  Bidirectional Learning for Domain Adaptation of Semantic Segmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Xiaofeng Liu,et al.  Confidence Regularized Self-Training , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[13]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[14]  Antonio M. López,et al.  The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Junqing Yu,et al.  Significance-Aware Information Bottleneck for Domain Adaptive Semantic Segmentation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[16]  Yi Zhang,et al.  PSANet: Point-wise Spatial Attention Network for Scene Parsing , 2018, ECCV.

[17]  Xiaoxiao Li,et al.  Semantic Image Segmentation via Deep Parsing Network , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[18]  Sebastian Ramos,et al.  The Cityscapes Dataset for Semantic Urban Scene Understanding , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Fengmao Lv,et al.  Constructing Self-Motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[20]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[21]  Yandong Tang,et al.  Recurrent Generative Adversarial Network for Face Completion , 2021, IEEE Transactions on Multimedia.

[22]  Ming Shao,et al.  Graph Adaptive Knowledge Transfer for Unsupervised Domain Adaptation , 2018, ECCV.

[23]  Trevor Darrell,et al.  FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation , 2016, ArXiv.

[24]  Changick Kim,et al.  Self-Ensembling With GAN-Based Data Augmentation for Domain Adaptation in Semantic Segmentation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[25]  Larry S. Davis,et al.  DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation , 2018, ECCV.

[26]  Deng Cai,et al.  Domain Adaptation for Semantic Segmentation With Maximum Squares Loss , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[27]  Swami Sankaranarayanan,et al.  Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[28]  Yi-Hsuan Tsai,et al.  Domain Adaptation for Structured Output via Discriminative Patch Representations , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[29]  Bernhard Schölkopf,et al.  Domain Adaptation under Target and Conditional Shift , 2013, ICML.

[30]  Min Sun,et al.  No More Discrimination: Cross City Adaptation of Road Scene Segmenters , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[31]  Luc Van Gool,et al.  DLOW: Domain Flow for Adaptation and Generalization , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Tatsuya Harada,et al.  Maximum Classifier Discrepancy for Unsupervised Domain Adaptation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[33]  Jan Kautz,et al.  Learning Affinity via Spatial Propagation Networks , 2017, NIPS.

[34]  Philip David,et al.  Domain Adaptation for Semantic Segmentation of Urban Scenes , 2017 .

[35]  Namil Kim,et al.  Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[36]  Zhengming Ding,et al.  Structure Preserving Generative Cross-Domain Learning , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Patrick Pérez,et al.  ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  Dongdong Hou,et al.  Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[39]  Chen-Yu Lee,et al.  Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Xiang Bai,et al.  Asymmetric Non-Local Neural Networks for Semantic Segmentation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[41]  Vladlen Koltun,et al.  Playing for Data: Ground Truth from Computer Games , 2016, ECCV.

[42]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[43]  Ming-Hsuan Yang,et al.  Learning to Adapt Structured Output Space for Semantic Segmentation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[44]  Xiaowei Xu,et al.  What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[45]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[46]  Yi Yang,et al.  Taking a Closer Look at Domain Shift: Category-Level Adversaries for Semantics Consistent Domain Adaptation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[47]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.