Skip to main content
SpringerLink
Log in
Book cover

European Conference on Computer Vision

ECCV 2022: Computer Vision – ECCV 2022 Workshops pp 308–325Cite as

Unleashing the Potential of Adaptation Models via Go-getting Domain Labels

  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13808))

Abstract

In this paper, we propose an embarrassingly simple yet highly effective adversarial domain adaptation (ADA) method. We view ADA problem primarily from an optimization perspective and point out a fundamental dilemma, in that the real-world data often exhibits an imbalanced distribution where the large data clusters typically dominate and bias the adaptation process. Unlike prior works that either attempt loss re-weighting or data re-sampling for alleviating this defect, we introduce a new concept of go-getting domain labels (Go-labels) to replace the original immutable domain labels on the fly. The reason why call it as “Go-labels” is because “go-getting” means able to deal with new or difficult situations easily, like here Go-labels adaptively transfer the model attention from over-studied aligned data to those overlooked samples, which allows each sample to be well studied (i.e., alleviating data imbalance influence) and fully unleashes the potential of adaption model. Albeit simple, this dynamic adversarial domain adaptation framework with Go-labels effectively addresses data imbalance issue and promotes adaptation. We demonstrate through theoretical insights, empirical results on real data as well as toy games that our method leads to efficient training without bells and whistles, while being robust to different backbones.

This is a preview of subscription content, log in via an institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   69.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   89.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

References

  1. Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: ICML, pp. 214–223. PMLR (2017)

    Google Scholar 

  2. Arpit, D., et al.: A closer look at memorization in deep networks. In: ICML, pp. 233–242. PMLR (2017)

    Google Scholar 

  3. Azadi, S., Olsson, C., Darrell, T., Goodfellow, I., Odena, A.: Discriminator rejection sampling. arXiv preprint arXiv:1810.06758 (2018)

  4. Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Vaughan, J.W.: A theory of learning from different domains. Mach. Learn. 79(1–2), 151–175 (2010)

    Article  MathSciNet  MATH  Google Scholar 

  5. Ben-David, S., Blitzer, J., Crammer, K., Pereira, F.: Analysis of representations for domain adaptation. In: NeurIPS, pp. 137–144 (2007)

    Google Scholar 

  6. Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Wortman, J.: Learning bounds for domain adaptation. In: NeurIPS, pp. 129–136 (2008)

    Google Scholar 

  7. Borgwardt, K.M., Gretton, A., Rasch, M.J., Kriegel, H.P., Schölkopf, B., Smola, A.J.: Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics 22(14), e49–e57 (2006)

    Article  Google Scholar 

  8. Chen, L., et al.: Reusing the task-specific classifier as a discriminator: discriminator-free adversarial domain adaptation. In: CVPR, pp. 7181–7190 (2022)

    Google Scholar 

  9. Chen, Q., Liu, Y., Wang, Z., Wassell, I., Chetty, K.: Re-weighted adversarial adaptation network for unsupervised domain adaptation. In: CVPR, pp. 7976–7985 (2018)

    Google Scholar 

  10. Cui, S., Wang, S., Zhuo, J., Li, L., Huang, Q., Tian, Q.: Towards discriminability and diversity: Batch nuclear-norm maximization under label insufficient situations. In: CVPR, pp. 3941–3950 (2020)

    Google Scholar 

  11. Cui, S., Wang, S., Zhuo, J., Su, C., Huang, Q., Tian, Q.: Gradually vanishing bridge for adversarial domain adaptation. In: CVPR, pp. 12455–12464 (2020)

    Google Scholar 

  12. Feldman, V.: Does learning require memorization? a short tale about a long tail. In: Proceedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing, pp. 954–959 (2020)

    Google Scholar 

  13. Feldman, V., Zhang, C.: What neural networks memorize and why: discovering the long tail via influence estimation. arXiv preprint arXiv:2008.03703 (2020)

  14. Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML, pp. 1180–1189. PMLR (2015)

    Google Scholar 

  15. Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2030–2096 (2016)

    MathSciNet  Google Scholar 

  16. Gao, Z., Zhang, S., Huang, K., Wang, Q., Zhong, C.: Gradient distribution alignment certificates better adversarial domain adaptation. In: ICCV, pp. 8937–8946 (2021)

    Google Scholar 

  17. Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: Improved training of wasserstein gans. arXiv preprint arXiv:1704.00028 (2017)

  18. Guo, T., et al.: On positive-unlabeled classification in gan. In: CVPR, pp. 8385–8393 (2020)

    Google Scholar 

  19. Haeusser, P., Frerix, T., Mordvintsev, A., Cremers, D.: Associative domain adaptation. In: ICCV, pp. 2765–2773 (2017)

    Google Scholar 

  20. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)

    Google Scholar 

  21. Hoffman, J., et al.: Cycada: cycle-consistent adversarial domain adaptation. In: ICML, pp. 1989–1998. PMLR (2018)

    Google Scholar 

  22. Huang, C., Li, Y., Loy, C.C., Tang, X.: Learning deep representation for imbalanced classification. In: CVPR, pp. 5375–5384 (2016)

    Google Scholar 

  23. Jiang, X., Lao, Q., Matwin, S., Havaei, M.: Implicit class-conditioned domain alignment for unsupervised domain adaptation. In: ICML, pp. 4816–4827. PMLR (2020)

    Google Scholar 

  24. Jin, X., Lan, C., Zeng, W., Chen, Z.: Re-energizing domain discriminator with sample relabeling for adversarial domain adaptation. In: ICCV (2021)

    Google Scholar 

  25. Jin, X., Lan, C., Zeng, W., Chen, Z.: Style normalization and restitution for domain generalization and adaptation. IEEE Trans. Multimedia 24, 3636–3651 (2021)

    Article  Google Scholar 

  26. Johansson, F.D., Sontag, D., Ranganath, R.: Support and invertibility in domain-invariant representations. In: AISTATS, pp. 527–536. PMLR (2019)

    Google Scholar 

  27. Kang, B., et al.: Decoupling representation and classifier for long-tailed recognition. In: ICLR (2019)

    Google Scholar 

  28. Kang, G., Jiang, L., Yang, Y., Hauptmann, A.G.: Contrastive adaptation network for unsupervised domain adaptation. In: CVPR, pp. 4893–4902 (2019)

    Google Scholar 

  29. Kifer, D., Ben-David, S., Gehrke, J.: Detecting change in data streams. In: VLDB, vol. 4, pp. 180–191. Toronto, Canada (2004)

    Google Scholar 

  30. Li, B., et al.: Rethinking distributional matching based domain adaptation. arXiv preprint arXiv:2006.13352 (2020)

  31. Li, S., Xie, M., Gong, K., Liu, C.H., Wang, Y., Li, W.: Transferable semantic augmentation for domain adaptation. In: CVPR, pp. 11516–11525 (2021)

    Google Scholar 

  32. Li, S., et al.: Semantic concentration for domain adaptation. In: ICCV, pp. 9102–9111 (2021)

    Google Scholar 

  33. Li, Y., et al.: Overcoming classifier imbalance for long-tail object detection with balanced group softmax. In: CVPR, pp. 10991–11000 (2020)

    Google Scholar 

  34. Liu, J., Sun, Y., Han, C., Dou, Z., Li, W.: Deep representation learning on long-tailed data: a learnable embedding augmentation perspective. In: CVPR, pp. 2970–2979 (2020)

    Google Scholar 

  35. Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: NeurIPS, pp. 1640–1650 (2018)

    Google Scholar 

  36. Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: ICML, pp. 2208–2217 (2017)

    Google Scholar 

  37. Lu, Z., Yang, Y., Zhu, X., Liu, C., Song, Y.Z., Xiang, T.: Stochastic classifiers for unsupervised domain adaptation. In: CVPR, pp. 9111–9120 (2020)

    Google Scholar 

  38. Luo, Y.W., Ren, C.X.: Conditional bures metric for domain adaptation. In: CVPR, pp. 13989–13998 (2021)

    Google Scholar 

  39. Nowozin, S., Cseke, B., Tomioka, R.: f-gan: training generative neural samplers using variational divergence minimization. In: NeurIPS (2016)

    Google Scholar 

  40. Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019)

  41. Pei, Z., Cao, Z., Long, M., Wang, J.: Multi-adversarial domain adaptation. In: AAAI, vol. 32 (2018)

    Google Scholar 

  42. Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., Wang, B.: Moment matching for multi-source domain adaptation. In: ICCV, pp. 1406–1415 (2019)

    Google Scholar 

  43. Peng, X., Usman, B., Kaushik, N., Hoffman, J., Wang, D., Saenko, K.: Visda: the visual domain adaptation challenge. arXiv preprint arXiv:1710.06924 (2017)

  44. Peng, Z., Huang, W., Guo, Z., Zhang, X., Jiao, J., Ye, Q.: Long-tailed distribution adaptation. In: ACMMM, pp. 3275–3282 (2021)

    Google Scholar 

  45. Raab, C., Vath, P., Meier, P., Schleif, F.M.: Bridging adversarial and statistical domain transfer via spectral adaptation networks. In: ACCV (2020)

    Google Scholar 

  46. Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 213–226. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15561-1_16

    Chapter  Google Scholar 

  47. Saito, K., Kim, D., Sclaroff, S., Saenko, K.: Universal domain adaptation through self supervision. In: NeurIPS (2020)

    Google Scholar 

  48. Saito, K., Ushiku, Y., Harada, T., Saenko, K.: Strong-weak distribution alignment for adaptive object detection. In: CVPR, pp. 6956–6965 (2019)

    Google Scholar 

  49. Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: CVPR, pp. 3723–3732 (2018)

    Google Scholar 

  50. Sankaranarayanan, S., Balaji, Y., Castillo, C.D., Chellappa, R.: Generate to adapt: aligning domains using generative adversarial networks. In: CVPR, pp. 8503–8512 (2018)

    Google Scholar 

  51. Shimodaira, H.: Improving predictive inference under covariate shift by weighting the log-likelihood function. J. Stat. Plan. Inference 90(2), 227–244 (2000)

    Article  MathSciNet  MATH  Google Scholar 

  52. Sinha, S., Zhao, Z., Alias Parth Goyal, A.G., Raffel, C.A., Odena, A.: Top-k training of gans: improving gan performance by throwing away bad samples. In: NeurIPS, vol. 33, pp. 14638–14649 (2020)

    Google Scholar 

  53. Sugiyama, M., Krauledat, M., Müller, K.R.: Covariate shift adaptation by importance weighted cross validation. J. Mach. Learn. Res. 8(5), 1–21 (2007)

    MathSciNet  MATH  Google Scholar 

  54. Sun, B., Feng, J., Saenko, K.: Return of frustratingly easy domain adaptation. In: AAAI, vol. 30 (2016)

    Google Scholar 

  55. Tan, S., Peng, X., Saenko, K.: Class-imbalanced domain adaptation: an empirical odyssey. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12535, pp. 585–602. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-66415-2_38

    Chapter  Google Scholar 

  56. Tang, H., Chen, K., Jia, K.: Unsupervised domain adaptation via structurally regularized deep clustering. In: CVPR, pp. 8725–8735 (2020)

    Google Scholar 

  57. Tang, H., Jia, K.: Discriminative adversarial domain adaptation. In: AAAI, vol. 34, pp. 5940–5947 (2020)

    Google Scholar 

  58. Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR 2011. pp. 1521–1528

    Google Scholar 

  59. Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR, pp. 7167–7176 (2017)

    Google Scholar 

  60. Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: CVPR (2017)

    Google Scholar 

  61. Wang, S., Zhang, L.: Self-adaptive re-weighted adversarial domain adaptation. IJCAI (2020)

    Google Scholar 

  62. Wei, G., Lan, C., Zeng, W., Chen, Z.: Metaalign: coordinating domain alignment and classification for unsupervised domain adaptation. In: CVPR (2021)

    Google Scholar 

  63. Wu, Y., Donahue, J., Balduzzi, D., Simonyan, K., Lillicrap, T.: Logan: latent optimisation for generative adversarial networks. arXiv preprint arXiv:1912.00953 (2019)

  64. Wu, Y., Winston, E., Kaushik, D., Lipton, Z.: Domain adaptation with asymmetrically-relaxed distribution alignment. In: ICML, pp. 6872–6881. PMLR (2019)

    Google Scholar 

  65. Xu, M., et al.: Adversarial domain adaptation with domain mixup. In: AAAI (2020)

    Google Scholar 

  66. Xu, R., Li, G., Yang, J., Lin, L.: Larger norm more transferable: an adaptive feature norm approach for unsupervised domain adaptation. In: ICCV, pp. 1426–1435 (2019)

    Google Scholar 

  67. Yang, L., Balaji, Y., Lim, S.-N., Shrivastava, A.: Curriculum manager for source selection in multi-source domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 608–624. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_36

    Chapter  Google Scholar 

  68. Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: NeurIPS (2014)

    Google Scholar 

  69. You, C., Li, C., Robinson, D.P., Vidal, R.: Scalable exemplar-based subspace clustering on class-imbalanced data. In: ECCV, pp. 67–83 (2018)

    Google Scholar 

  70. Zhang, J., Ding, Z., Li, W., Ogunbona, P.: Importance weighted adversarial nets for partial domain adaptation. In: CVPR, pp. 8156–8164 (2018)

    Google Scholar 

  71. Zhang, X., Fang, Z., Wen, Y., Li, Z., Qiao, Y.: Range loss for deep face recognition with long-tailed training data. In: ICCV, pp. 5409–5418 (2017)

    Google Scholar 

  72. Zhang, Y., Tang, H., Jia, K., Tan, M.: Domain-symmetric networks for adversarial domain adaptation. In: CVPR, pp. 5031–5040 (2019)

    Google Scholar 

  73. Zhang, Y., Liu, T., Long, M., Jordan, M.I.: Bridging theory and algorithm for domain adaptation. In: ICML (2019)

    Google Scholar 

  74. Zhao, H., Des Combes, R.T., Zhang, K., Gordon, G.: On learning invariant representations for domain adaptation. In: ICML, pp. 7523–7532. PMLR (2019)

    Google Scholar 

  75. Zhao, H., Zhang, S., Wu, G., Moura, J.M., Costeira, J.P., Gordon, G.J.: Adversarial multiple source domain adaptation. In: NeurIPS, pp. 8559–8570 (2018)

    Google Scholar 

  76. Zhou, B., Cui, Q., Wei, X.S., Chen, Z.M.: Bbn: bilateral-branch network with cumulative learning for long-tailed visual recognition. In: CVPR, pp. 9719–9728 (2020)

    Google Scholar 

Download references

Acknowledgments

This work was supported in part by NSFC under Grant U1908209, 62021001 and the National Key Research and Development Program of China 2018AAA0101400. This work was also supported in part by the Advanced Research and Technology Innovation Centre (ARTIC), the National University of Singapore under Grant (project number: A-0005947-21-00).

Author information

Authors and Affiliations

  1. Eastern Institute for Advanced Study, Ningbo, China

    Xin Jin

  2. Alibaba Group, Hangzhou, China

    Tianyu He, Xu Shen, Jianqiang Huang & Xian-Sheng Hua

  3. The University of Sydney, Sydney, Australia

    Songhua Wu & Tongliang Liu

  4. National University of Singapore, Singapore, Singapore

    Jingwen Ye & Xinchao Wang

  5. University of Science and Technology of China, Hefei, China

    Zhibo Chen

Authors
  1. Xin Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tianyu He
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xu Shen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Songhua Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Tongliang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jingwen Ye
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Xinchao Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Jianqiang Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Zhibo Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Xian-Sheng Hua
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xin Jin .

Editor information

Editors and Affiliations

  1. IBM Research AI and MIT-IBM Watson AI Lab, Haifa, Israel

    Leonid Karlinsky

  2. Technion – Israel Institute of Technology, Haifa, Israel

    Tomer Michaeli

  3. Kyoto University, Kyoto, Japan

    Ko Nishino

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 1268 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Jin, X. et al. (2023). Unleashing the Potential of Adaptation Models via Go-getting Domain Labels. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13808. Springer, Cham. https://doi.org/10.1007/978-3-031-25085-9_18

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-25085-9_18

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-25084-2

  • Online ISBN: 978-3-031-25085-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation