Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

FREEDOM: Target Label & Source Data & Domain Information-Free Multi-Source Domain Adaptation for Unsupervised Personalization (2307.02493v1)

Published 4 Jul 2023 in cs.LG and cs.AI

Abstract: From a service perspective, Multi-Source Domain Adaptation (MSDA) is a promising scenario to adapt a deployed model to a client's dataset. It can provide adaptation without a target label and support the case where a source dataset is constructed from multiple domains. However, it is impractical, wherein its training heavily relies on prior domain information of the multi-source dataset -- how many domains exist and the domain label of each data sample. Moreover, MSDA requires both source and target datasets simultaneously (physically), causing storage limitations on the client device or data privacy issues by transferring client data to a server. For a more practical scenario of model adaptation from a service provider's point of view, we relax these constraints and present a novel problem scenario of Three-Free Domain Adaptation, namely TFDA, where 1) target labels, 2) source dataset, and mostly 3) source domain information (domain labels + the number of domains) are unavailable. Under the problem scenario, we propose a practical adaptation framework called FREEDOM. It leverages the power of the generative model, disentangling data into class and style aspects, where the style is defined as the class-independent information from the source data and designed with a nonparametric Bayesian approach. In the adaptation stage, FREEDOM aims to match the source class distribution with the target's under the philosophy that class distribution is consistent even if the style is different; after then, only part of the classification model is deployed as a personalized network. As a result, FREEDOM achieves state-of-the-art or comparable performance even without domain information, with reduced final model size on the target side, independent of the number of source domains.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. A. Torralba and A. A. Efros, “Unbiased look at dataset bias,” in CVPR 2011, 2011, pp. 1521–1528.
  2. A. Gretton, A. Smola, J. Huang, M. Schmittfull, K. Borgwardt, and B. Schölkopf, “Covariate shift by kernel mean matching,” Dataset shift in machine learning, vol. 3, no. 4, p. 5, 2009.
  3. Y. Ganin and V. Lempitsky, “Unsupervised domain adaptation by backpropagation,” in International conference on machine learning.   PMLR, 2015, pp. 1180–1189.
  4. R. Xu, Z. Chen, W. Zuo, J. Yan, and L. Lin, “Deep cocktail network: Multi-source unsupervised domain adaptation with category shift,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.
  5. H. Wang, M. Xu, B. Ni, and W. Zhang, “Learning to combine: Knowledge aggregation for multi-source domain adaptation,” in European Conference on Computer Vision.   Springer, 2020, pp. 727–744.
  6. J. Liang, D. Hu, and J. Feng, “Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation,” in Proceedings of the 37th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research, H. D. III and A. Singh, Eds., vol. 119.   PMLR, 13–18 Jul 2020, pp. 6028–6039.
  7. J. N. Kundu, N. Venkat, R. M. V, and R. V. Babu, “Universal source-free domain adaptation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020.
  8. S. Yang, Y. Wang, J. van de Weijer, L. Herranz, and S. Jui, “Casting a bait for offline and online source-free domain adaptation,” arXiv preprint arXiv:2010.12427, 2020.
  9. Y. Kim, D. Cho, K. Han, P. Panda, and S. Hong, “Domain adaptation without source data,” IEEE Transactions on Artificial Intelligence, vol. 2, no. 6, pp. 508–518, 2021.
  10. S. M. Ahmed, D. S. Raychaudhuri, S. Paul, S. Oymak, and A. K. Roy-Chowdhury, “Unsupervised multi-source domain adaptation without access to source data,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 10 103–10 112.
  11. J. Dong, Z. Fang, A. Liu, G. Sun, and T. Liu, “Confident anchor-induced multi-source free domain adaptation,” in Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P. Liang, and J. W. Vaughan, Eds., vol. 34.   Curran Associates, Inc., 2021, pp. 2848–2860.
  12. J. Hoffman, B. Kulis, T. Darrell, and K. Saenko, “Discovering latent domains for multisource domain adaptation,” in European Conference on Computer Vision.   Springer, 2012, pp. 702–715.
  13. F. M. Carlucci, A. D’Innocente, S. Bucci, B. Caputo, and T. Tommasi, “Domain generalization by solving jigsaw puzzles,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.
  14. M. Mancini, L. Porzi, S. R. Bulo, B. Caputo, and E. Ricci, “Boosting domain adaptation by discovering latent domains,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 3771–3780.
  15. C. Xiong, S. McCloskey, S.-H. Hsieh, and J. Corso, “Latent domains modeling for visual domain adaptation,” Proceedings of the AAAI Conference on Artificial Intelligence, Jun. 2014.
  16. H. Li, W. Li, and S. Wang, “Discovering and incorporating latent target-domains for domain adaptation,” Pattern Recognition, vol. 108, p. 107536, 2020.
  17. S. Ben-David, J. Blitzer, K. Crammer, A. Kulesza, F. Pereira, and J. W. Vaughan, “A theory of learning from different domains,” Machine learning, vol. 79, no. 1, pp. 151–175, 2010.
  18. Y. Mansour, M. Mohri, and A. Rostamizadeh, “Domain adaptation: Learning bounds and algorithms,” arXiv preprint arXiv:0902.3430, 2009.
  19. M. Long, Y. Cao, J. Wang, and M. Jordan, “Learning transferable features with deep adaptation networks,” in Proceedings of the 32nd International Conference on Machine Learning, ser. Proceedings of Machine Learning Research, F. Bach and D. Blei, Eds., vol. 37.   Lille, France: PMLR, 07–09 Jul 2015, pp. 97–105.
  20. B. Sun, J. Feng, and K. Saenko, “Correlation alignment for unsupervised domain adaptation,” in Domain Adaptation in Computer Vision Applications.   Springer, 2017, pp. 153–171.
  21. A. Gretton, K. M. Borgwardt, M. J. Rasch, B. Schölkopf, and A. Smola, “A kernel two-sample test,” The Journal of Machine Learning Research, vol. 13, no. 1, pp. 723–773, 2012.
  22. H. Rangwani, S. K. Aithal, M. Mishra, A. Jain, and V. B. Radhakrishnan, “A closer look at smoothness in domain adversarial training,” in International Conference on Machine Learning.   PMLR, 2022, pp. 18 378–18 399.
  23. R. Cai, Z. Li, P. Wei, J. Qiao, K. Zhang, and Z. Hao, “Learning disentangled semantic representation for domain adaptation,” in IJCAI: proceedings of the conference, vol. 2019.   NIH Public Access, 2019, p. 2060.
  24. S. Sankaranarayanan, Y. Balaji, C. D. Castillo, and R. Chellappa, “Generate to adapt: Aligning domains using generative adversarial networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 8503–8512.
  25. J. Hoffman, M. Mohri, and N. Zhang, “Algorithms and theory for multiple-source adaptation,” Advances in Neural Information Processing Systems, vol. 31, 2018.
  26. S. Zhao, G. Wang, S. Zhang, Y. Gu, Y. Li, Z. Song, P. Xu, R. Hu, H. Chai, and K. Keutzer, “Multi-source distilling domain adaptation,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 12 975–12 983, Apr. 2020.
  27. X. Peng, Q. Bai, X. Xia, Z. Huang, K. Saenko, and B. Wang, “Moment matching for multi-source domain adaptation,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2019.
  28. N. Venkat, J. N. Kundu, D. Singh, A. Revanur et al., “Your classifier can secretly suffice multi-source domain adaptation,” Advances in Neural Information Processing Systems, vol. 33, pp. 4647–4659, 2020.
  29. B. Gong, K. Grauman, and F. Sha, “Reshaping visual datasets for domain adaptation,” Advances in Neural Information Processing Systems, vol. 26, 2013.
  30. X. Wu, J. Chen, F. Yu, M. Yao, and J. Luo, “Joint learning of multiple latent domains and deep representations for domain adaptation,” IEEE transactions on cybernetics, vol. 51, no. 5, pp. 2676–2687, 2019.
  31. M. Mancini, L. Porzi, F. Cermelli, and B. Caputo, “Discovering latent domains for unsupervised domain adaptation through consistency,” in International Conference on Image Analysis and Processing.   Springer, 2019, pp. 390–401.
  32. R. Li, Q. Jiao, W. Cao, H.-S. Wong, and S. Wu, “Model adaptation: Unsupervised domain adaptation without source data,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020.
  33. D. P. Kingma and M. Welling, “Auto-encoding variational bayes,” arXiv preprint arXiv:1312.6114, 2013.
  34. D. M. Blei and M. I. Jordan, “Variational inference for dirichlet process mixtures,” Bayesian analysis, vol. 1, no. 1, pp. 121–143, 2006.
  35. Y. Jeong and H. O. Song, “Learning discrete and continuous factors of data via alternating disentanglement,” in International Conference on Machine Learning.   PMLR, 2019, pp. 3091–3099.
  36. K. Saenko, B. Kulis, M. Fritz, and T. Darrell, “Adapting visual category models to new domains,” in European conference on computer vision.   Springer, 2010, pp. 213–226.
  37. H. Venkateswara, J. Eusebio, S. Chakraborty, and S. Panchanathan, “Deep hashing network for unsupervised domain adaptation,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017.
  38. H. Zhao, S. Zhang, G. Wu, J. M. F. Moura, J. P. Costeira, and G. J. Gordon, “Adversarial multiple source domain adaptation,” 2018.
  39. V.-A. Nguyen, T. Nguyen, T. Le, Q. H. Tran, and D. Phung, “Stem: An approach to multi-source domain adaptation with guarantees,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2021, pp. 9352–9363.
  40. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala, “Pytorch: An imperative style, high-performance deep learning library,” in Advances in Neural Information Processing Systems 32.   Curran Associates, Inc., 2019, pp. 8024–8035. [Online]. Available: http://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf
  41. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
  42. Z. Jiang, Y. Zheng, H. Tan, B. Tang, and H. Zhou, “Variational deep embedding: An unsupervised and generative approach to clustering,” in IJCAI, 2017.
  43. R. Müller, S. Kornblith, and G. E. Hinton, “When does label smoothing help?” Advances in neural information processing systems, vol. 32, 2019.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now