Attracting and dispersing: a simple approach for source-free domain adaptation
Article No.: 420, Pages 5802 - 5815
Abstract
We propose a simple but effective source-free domain adaptation (SFDA) method. Treating SFDA as an unsupervised clustering problem and following the intuition that local neighbors in feature space should have more similar predictions than other features, we propose to optimize an objective of prediction consistency. This objective encourages local neighborhood features in feature space to have similar predictions while features farther away in feature space have dissimilar predictions, leading to efficient feature clustering and cluster assignment simultaneously. For efficient training, we seek to optimize an upper-bound of the objective resulting in two simple terms. Furthermore, we relate popular existing methods in domain adaptation, source-free domain adaptation and contrastive learning via the perspective of discriminability and diversity. The experimental results prove the superiority of our method, and our method can be adopted as a simple but strong baseline for future research in SFDA. Our method can be also adapted to source-free open-set and partial-set DA which further shows the generalization ability of our method.
References
[1]
Silvia Bucci, Mohammad Reza Loghmani, and Tatiana Tommasi. On the effectiveness of image rotation for open set domain adaptation. In European Conference on Computer Vision, pages 422-438. Springer, 2020.
[2]
Jianlong Chang, Lingfeng Wang, Gaofeng Meng, Shiming Xiang, and Chunhong Pan. Deep adaptive image clustering. In ICCV, pages 5879-5887, 2017.
[3]
Xinyang Chen, Sinan Wang, Mingsheng Long, and Jianmin Wang. Transferability vs. discriminability: Batch spectral penalization for adversarial domain adaptation. In ICML, pages 1081-1090, 2019.
[4]
Safa Cicek and Stefano Soatto. Unsupervised domain adaptation via regularized conditional alignment. In ICCV, pages 1416-1425, 2019.
[5]
Shuhao Cui, Shuhui Wang, Junbao Zhuo, Liang Li, Qingming Huang, and Qi Tian. Towards discriminability and diversity: Batch nuclear-norm maximization under label insufficient situations. CVPR, 2020.
[6]
Shuhao Cui, Shuhui Wang, Junbao Zhuo, Liang Li, Qingming Huang, and Qi Tian. Fast batch nuclear-norm maximization and minimization for robust domain adaptation. arXiv preprint arXiv:2107.06154, 2021.
[7]
Zhijie Deng, Yucen Luo, and Jun Zhu. Cluster alignment with a teacher for unsupervised domain adaptation. In ICCV, pages 9944-9953, 2019.
[8]
Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, and Andrew Zisserman. With a little help from my friends: Nearest-neighbor contrastive learning of visual representations. ICCV, 2021.
[9]
Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, Fran�ois Laviolette, Mario Marchand, and Victor Lempitsky. Domain-adversarial training of neural networks. JMLR, 17(1):2096-2030, 2016.
[10]
Jacob Goldberger, Geoffrey E Hinton, Sam Roweis, and Russ R Salakhutdinov. Neighbourhood components analysis. NIPS, 17, 2004.
[11]
Ryan Gomes, Andreas Krause, and Pietro Perona. Discriminative clustering by regularized information maximization. In NIPS, 2010.
[12]
Boqing Gong, Yuan Shi, Fei Sha, and Kristen Grauman. Geodesic flow kernel for unsupervised domain adaptation. In CVPR, pages 2066-2073. IEEE, 2012.
[13]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In CVPR, pages 770-778, 2016.
[14]
Weihua Hu, Takeru Miyato, Seiya Tokui, Eiichi Matsumoto, and Masashi Sugiyama. Learning discrete representations via information maximizing self-augmented training. In ICML, pages 1558-1567, 2017.
[15]
Jiaxing Huang, Dayan Guan, Aoran Xiao, and Shijian Lu. Model adaptation: Historical contrastive learning for unsupervised domain adaptation without source data. NeurIPS, 34, 2021.
[16]
Zhizhong Huang, Jie Chen, Junping Zhang, and Hongming Shan. Exploring non-contrastive representation learning for deep clustering. arXiv preprint arXiv:2111.11821, 2021.
[17]
Sergey Ioffe and Christian Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167, 2015.
[18]
Xu Ji, Joao F Henriques, and Andrea Vedaldi. Invariant information clustering for unsupervised image classification and segmentation. In ICCV, pages 9865-9874, 2019.
[19]
Ying Jin, Ximei Wang, Mingsheng Long, and Jianmin Wang. Minimum class confusion for versatile domain adaptation. ECCV, 2020.
[20]
Jogendra Nath Kundu, Naveen Venkat, and R Venkatesh Babu. Universal source-free domain adaptation. CVPR, 2020.
[21]
Jogendra Nath Kundu, Naveen Venkat, Ambareesh Revanur, R Venkatesh Babu, et al. Towards inheritable models for open-set domain adaptation. In CVPR, pages 12376-12385, 2020.
[22]
Chen-Yu Lee, Tanmay Batra, Mohammad Haris Baig, and Daniel Ulbricht. Sliced wasserstein discrepancy for unsupervised domain adaptation. In CVPR, pages 10285-10295, 2019.
[23]
Junnan Li, Pan Zhou, Caiming Xiong, and Steven Hoi. Prototypical contrastive learning of unsupervised representations. In ICLR, 2021.
[24]
Rui Li, Qianfen Jiao, Wenming Cao, Hau-San Wong, and Si Wu. Model adaptation: Unsupervised domain adaptation without source data. In CVPR, pages 9641-9650, 2020.
[25]
Yunfan Li, Peng Hu, Zitao Liu, Dezhong Peng, Joey Tianyi Zhou, and Xi Peng. Contrastive clustering. In AAAI, 2021.
[26]
Jian Liang, Dapeng Hu, and Jiashi Feng. Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. ICML, 2020.
[27]
Jian Liang, Dapeng Hu, and Jiashi Feng. Domain adaptation with auxiliary target domain-oriented classifier. In CVPR, pages 16632-16642, 2021.
[28]
Jian Liang, Dapeng Hu, Ran He, and Jiashi Feng. Distill and fine-tune: Effective adaptation from a black-box source model. CVPR, 2022.
[29]
Jian Liang, Dapeng Hu, Yunbo Wang, Ran He, and Jiashi Feng. Source data-absent unsupervised domain adaptation through hypothesis transfer and labeling transfer. arXiv preprint arXiv:2012.07297, 2020.
[30]
Jian Liang, Dapeng Hu, Yunbo Wang, Ran He, and Jiashi Feng. Source data-absent unsupervised domain adaptation through hypothesis transfer and labeling transfer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.
[31]
Hong Liu, Jianmin Wang, and Mingsheng Long. Cycle self-training for domain adaptation. In NeurIPS, 2021.
[32]
Mingsheng Long, Yue Cao, Zhangjie Cao, Jianmin Wang, and Michael I Jordan. Transferable representation learning with deep adaptation networks. TPAMI, 41(12):3071-3085, 2018.
[33]
Mingsheng Long, Yue Cao, Jianmin Wang, and Michael I Jordan. Learning transferable features with deep adaptation networks. ICML, 2015.
[34]
Mingsheng Long, Zhangjie Cao, Jianmin Wang, and Michael I Jordan. Conditional adversarial domain adaptation. In NIPS, pages 1647-1657, 2018.
[35]
Mingsheng Long, Han Zhu, Jianmin Wang, and Michael I Jordan. Unsupervised domain adaptation with residual transfer networks. In NIPS, pages 136-144, 2016.
[36]
Zhihe Lu, Yongxin Yang, Xiatian Zhu, Cong Liu, Yi-Zhe Song, and Tao Xiang. Stochastic classifiers for unsupervised domain adaptation. In CVPR, pages 9111-9120, 2020.
[37]
Aaron van den Oord, Yazhe Li, and Oriol Vinyals. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748, 2018.
[38]
Sinno Jialin Pan and Qiang Yang. A survey on transfer learning. TKDE, 22(10):1345-1359, 2009.
[39]
Xingchao Peng, Ben Usman, Neela Kaushik, Judy Hoffman, Dequan Wang, and Kate Saenko. Visda: The visual domain adaptation challenge. arXiv preprint arXiv:1710.06924, 2017.
[40]
Simone Romano, James Bailey, Vinh Nguyen, and Karin Verspoor. Standardized mutual information for clustering comparisons: one step further in adjustment for chance. In ICML, pages 1143-1151, 2014.
[41]
Kate Saenko, Brian Kulis, Mario Fritz, and Trevor Darrell. Adapting visual category models to new domains. In ECCV, pages 213-226. Springer, 2010.
[42]
Kuniaki Saito, Donghyun Kim, Stan Sclaroff, and Kate Saenko. Universal domain adaptation through self supervision. NeurIPS, 33, 2020.
[43]
Kuniaki Saito, Donghyun Kim, Piotr Teterwak, Stan Sclaroff, Trevor Darrell, and Kate Saenko. Tune it the right way: Unsupervised validation of domain adaptation via soft neighborhood density. In ICCV, pages 9184-9193, 2021.
[44]
Kuniaki Saito, Kohei Watanabe, Yoshitaka Ushiku, and Tatsuya Harada. Maximum classifier discrepancy for unsupervised domain adaptation. In CVPR, pages 3723-3732, 2018.
[45]
Tim Salimans and Diederik P Kingma. Weight normalization: A simple reparameterization to accelerate training of deep neural networks. arXiv preprint arXiv:1602.07868, 2016.
[46]
Yuming Shen, Ziyi Shen, Menghan Wang, Jie Qin, Philip HS Torr, and Ling Shao. You never cluster alone. In NeurIPS, 2021.
[47]
Rui Shu, Hung H Bui, Hirokazu Narui, and Stefano Ermon. A dirt-t approach to unsupervised domain adaptation. ICLR, 2018.
[48]
Jost Tobias Springenberg. Unsupervised and semi-supervised learning with categorical generative adversarial networks. In ICLR, 2015.
[49]
Baochen Sun, Jiashi Feng, and Kate Saenko. Return of frustratingly easy domain adaptation. In AAAI, 2016.
[50]
Hui Tang, Ke Chen, and Kui Jia. Unsupervised domain adaptation via structurally regularized deep clustering. In CVPR, pages 8725-8735, 2020.
[51]
Tsung Wei Tsai, Chongxuan Li, and Jun Zhu. Mice: Mixture of contrastive experts for unsupervised image clustering. In ICLR, 2021.
[52]
Eric Tzeng, Judy Hoffman, Kate Saenko, and Trevor Darrell. Adversarial discriminative domain adaptation. In CVPR, pages 7167-7176, 2017.
[53]
Eric Tzeng, Judy Hoffman, Ning Zhang, Kate Saenko, and Trevor Darrell. Deep domain confusion: Maximizing for domain invariance. arXiv preprint arXiv:1412.3474, 2014.
[54]
Hemanth Venkateswara, Jose Eusebio, Shayok Chakraborty, and Sethuraman Panchanathan. Deep hashing network for unsupervised domain adaptation. In CVPR, pages 5018-5027, 2017.
[55]
Qin Wang, Olga Fink, Luc Van Gool, and Dengxin Dai. Continual test-time domain adaptation. CVPR, 2022.
[56]
Tongzhou Wang and Phillip Isola. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In ICML, pages 9929-9939. PMLR, 2020.
[57]
Ximei Wang, Liang Li, Weirui Ye, Mingsheng Long, and Jianmin Wang. Transferable attention for domain adaptation. In AAAI, volume 33, pages 5345-5352, 2019.
[58]
Jianlong Wu, Keyu Long, Fei Wang, Chen Qian, Cheng Li, Zhouchen Lin, and Hongbin Zha. Deep comprehensive correlation mining for image clustering. In ICCV, pages 8150-8159, 2019.
[59]
Yuan Wu, Diana Inkpen, and Ahmed El-Roby. Dual mixup regularized learning for adversarial domain adaptation. ECCV, 2020.
[60]
Zhirong Wu, Yuanjun Xiong, Stella X Yu, and Dahua Lin. Unsupervised feature learning via non-parametric instance discrimination. In CVPR, pages 3733-3742, 2018.
[61]
Haifeng Xia, Handong Zhao, and Zhengming Ding. Adaptive adversarial network for source-free domain adaptation. In ICCV, pages 9010-9019, 2021.
[62]
Renjun Xu, Pelen Liu, Liyan Wang, Chao Chen, and Jindong Wang. Reliable weighted optimal transport for unsupervised domain adaptation. In CVPR, pages 4394-4403, 2020.
[63]
Ruijia Xu, Guanbin Li, Jihan Yang, and Liang Lin. Larger norm more transferable: An adaptive feature norm approach for unsupervised domain adaptation. In ICCV, October 2019.
[64]
Shiqi Yang, Joost van de Weijer, Luis Herranz, Shangling Jui, et al. Exploiting the intrinsic neighborhood structure for source-free domain adaptation. NeurIPS, 34, 2021.
[65]
Shiqi Yang, Yaxing Wang, Joost van de Weijer, Luis Herranz, and Shangling Jui. Unsupervised domain adaptation without source data by casting a bait. arXiv preprint arXiv:2010.12427, 2020.
[66]
Shiqi Yang, Yaxing Wang, Joost van de Weijer, Luis Herranz, and Shangling Jui. Generalized source-free domain adaptation. In ICCV, pages 8978-8987, 2021.
[67]
Yabin Zhang, Bin Deng, Kui Jia, and Lei Zhang. Label propagation with augmented anchors: A simple semi-supervised learning baseline for unsupervised domain adaptation. In ECCV, pages 781-797, 2020.
[68]
Yabin Zhang, Hui Tang, Kui Jia, and Mingkui Tan. Domain-symmetric networks for adversarial domain adaptation. In CVPR, pages 5031-5040, 2019.
[69]
Yuchen Zhang, Tianle Liu, Mingsheng Long, and Michael Jordan. Bridging theory and algorithm for domain adaptation. In ICML, pages 7404-7413, 2019.
[70]
Chengxu Zhuang, Alex Lin Zhai, and Daniel Yamins. Local aggregation for unsupervised learning of visual embeddings. In ICCV, pages 6002-6012, 2019.
Index Terms
- Attracting and dispersing: a simple approach for source-free domain adaptation
Index terms have been assigned to the content through auto-classification.
Recommendations
MP-Trees: A Packing-Based Macro Placement Algorithm for Modern Mixed-Size Designs
In this paper, we present a new multipacking-tree (MP-tree) representation for macro placements to handle modern mixed-size designs with large macros and high chip utilization rates. Based on binary trees, the MP-tree is very efficient, effective, and ...
MP-trees: a packing-based macro placement algorithm for mixed-size designs
DAC '07: Proceedings of the 44th annual Design Automation ConferenceIn this paper, we present a new multi-packing tree (MP-tree) representation for macro placement to handle mixed-size designs. Based on binary trees, the MP-tree is very efficient, effective, and flexible for handling macro placement with various ...
A robust detailed placement for mixed-size IC designs
ASP-DAC '06: Proceedings of the 2006 Asia and South Pacific Design Automation ConferenceThe rapid increase in IC design complexity and wide-spread use of intellectual-property (IP) blocks have made the so-called mixed-size placement a very important topic in recent years. Although several algorithms have been proposed for mixed-sized ...
Comments
Information & Contributors
Information
Published In
November 2022
39114 pages
ISBN:9781713871088
- Editors:
- S. Koyejo,
- S. Mohamed,
- A. Agarwal,
- D. Belgrave,
- K. Cho,
- A. Oh
Copyright � 2022 Neural Information Processing Systems Foundation, Inc.
Publisher
Curran Associates Inc.
Red Hook, NY, United States
Publication History
Published: 03 April 2024
Qualifiers
- Research-article
- Research
- Refereed limited
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 21 Oct 2024