Universal Domain Adaptation

Domain adaptation aims to transfer knowledge in the presence of the domain gap. Existing domain adaptation methods rely on rich prior knowledge about the relationship between the label sets of source and target domains, which greatly limits their application in the wild. This paper introduces Universal Domain Adaptation (UDA) that requires no prior knowledge on the label sets. For a given source label set and a target label set, they may contain a common label set and hold a private label set respectively, bringing up an additional category gap. UDA requires a model to either (1) classify the target sample correctly if it is associated with a label in the common label set, or (2) mark it as ``unknown'' otherwise. More importantly, a UDA model should work stably against a wide spectrum of commonness (the proportion of the common label set over the complete label set) so that it can handle real-world problems with unknown target label sets. To solve the universal domain adaptation problem, we propose Universal Adaptation Network (UAN). It quantifies sample-level transferability to discover the common label set and the label sets private to each domain, thereby promoting the adaptation in the automatically discovered common label set and recognizing the ``unknown'' samples successfully. A thorough evaluation shows that UAN outperforms the state of the art closed set, partial and open set domain adaptation methods in the novel UDA setting.

[1]  Taesung Park,et al.  CyCADA: Cycle-Consistent Adversarial Domain Adaptation , 2017, ICML.

[2]  Juergen Gall,et al.  Open Set Domain Adaptation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[3]  Kilian Q. Weinberger,et al.  On Calibration of Modern Neural Networks , 2017, ICML.

[4]  Michael I. Jordan,et al.  Unsupervised Domain Adaptation with Residual Transfer Networks , 2016, NIPS.

[5]  Ivor W. Tsang,et al.  Domain Transfer Multiple Kernel Learning , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Daniel Cremers,et al.  Associative Domain Adaptation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[7]  Sethuraman Panchanathan,et al.  Deep Hashing Network for Unsupervised Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Kaiming He,et al.  Mask R-CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[10]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[11]  Trevor Darrell,et al.  Simultaneous Deep Transfer Across Domains and Tasks , 2015, ICCV.

[12]  Jeff G. Schneider,et al.  Flexible Transfer Learning under Support and Model Shift , 2014, NIPS.

[13]  Michael I. Jordan,et al.  Learning Transferable Features with Deep Adaptation Networks , 2015, ICML.

[14]  Jing Zhang,et al.  Importance Weighted Adversarial Nets for Partial Domain Adaptation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[15]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[17]  Yi Yang,et al.  Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization , 2018, ECCV.

[18]  Ivor W. Tsang,et al.  Domain Adaptation via Transfer Component Analysis , 2009, IEEE Transactions on Neural Networks.

[19]  Kate Saenko,et al.  VisDA: A Synthetic-to-Real Benchmark for Visual Domain Adaptation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[20]  Nicolas Courty,et al.  DeepJDOT: Deep Joint distribution optimal transport for unsupervised domain adaptation , 2018, ECCV.

[21]  Chuan Chen,et al.  Learning Semantic Representations for Unsupervised Domain Adaptation , 2018, ICML.

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

[23]  Tatsuya Harada,et al.  Open Set Domain Adaptation by Backpropagation , 2018, ECCV.

[24]  Shang-Hong Lai,et al.  AugGAN: Cross Domain Adaptation with GAN-Based Data Augmentation , 2018, ECCV.

[25]  Trevor Darrell,et al.  Adapting Visual Category Models to New Domains , 2010, ECCV.

[26]  Carlos D. Castillo,et al.  Generate to Adapt: Aligning Domains Using Generative Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[27]  Yoshua Bengio,et al.  Semi-supervised Learning by Entropy Minimization , 2004, CAP.

[28]  Silvio Savarese,et al.  Adversarial Feature Augmentation for Unsupervised Domain Adaptation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[29]  Yuan Shi,et al.  Geodesic flow kernel for unsupervised domain adaptation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[30]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[31]  Jianmin Wang,et al.  Partial Transfer Learning with Selective Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[32]  Trevor Darrell,et al.  Adversarial Discriminative Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Sheng-De Wang,et al.  Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[34]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[35]  Trevor Darrell,et al.  Deep Domain Confusion: Maximizing for Domain Invariance , 2014, CVPR 2014.

[36]  Fabio Maria Carlucci,et al.  From Source to Target and Back: Symmetric Bi-Directional Adaptive GAN , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[37]  Dumitru Erhan,et al.  Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[39]  Edwin Lughofer,et al.  Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning , 2017, ICLR.

[40]  Dong Xu,et al.  Collaborative and Adversarial Network for Unsupervised Domain Adaptation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[41]  Hong Liu,et al.  Separate to Adapt: Open Set Domain Adaptation via Progressive Separation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[42]  Shiguang Shan,et al.  Duplex Generative Adversarial Network for Unsupervised Domain Adaptation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[43]  Jianmin Wang,et al.  Learning to Transfer Examples for Partial Domain Adaptation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[44]  Fabio Maria Carlucci,et al.  AutoDIAL: Automatic Domain Alignment Layers , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[45]  Ian J. Wassell,et al.  Re-weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[46]  Jianmin Wang,et al.  Partial Adversarial Domain Adaptation , 2018, ECCV.

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

[48]  David J. Kriegman,et al.  Image to Image Translation for Domain Adaptation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[49]  Fei-Fei Li,et al.  Label Efficient Learning of Transferable Representations acrosss Domains and Tasks , 2017, NIPS.