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.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: ICML, pp. 214–223. PMLR (2017)
Arpit, D., et al.: A closer look at memorization in deep networks. In: ICML, pp. 233–242. PMLR (2017)
Azadi, S., Olsson, C., Darrell, T., Goodfellow, I., Odena, A.: Discriminator rejection sampling. arXiv preprint arXiv:1810.06758 (2018)
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)
Ben-David, S., Blitzer, J., Crammer, K., Pereira, F.: Analysis of representations for domain adaptation. In: NeurIPS, pp. 137–144 (2007)
Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Wortman, J.: Learning bounds for domain adaptation. In: NeurIPS, pp. 129–136 (2008)
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)
Chen, L., et al.: Reusing the task-specific classifier as a discriminator: discriminator-free adversarial domain adaptation. In: CVPR, pp. 7181–7190 (2022)
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)
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)
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)
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)
Feldman, V., Zhang, C.: What neural networks memorize and why: discovering the long tail via influence estimation. arXiv preprint arXiv:2008.03703 (2020)
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML, pp. 1180–1189. PMLR (2015)
Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2030–2096 (2016)
Gao, Z., Zhang, S., Huang, K., Wang, Q., Zhong, C.: Gradient distribution alignment certificates better adversarial domain adaptation. In: ICCV, pp. 8937–8946 (2021)
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: Improved training of wasserstein gans. arXiv preprint arXiv:1704.00028 (2017)
Guo, T., et al.: On positive-unlabeled classification in gan. In: CVPR, pp. 8385–8393 (2020)
Haeusser, P., Frerix, T., Mordvintsev, A., Cremers, D.: Associative domain adaptation. In: ICCV, pp. 2765–2773 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Hoffman, J., et al.: Cycada: cycle-consistent adversarial domain adaptation. In: ICML, pp. 1989–1998. PMLR (2018)
Huang, C., Li, Y., Loy, C.C., Tang, X.: Learning deep representation for imbalanced classification. In: CVPR, pp. 5375–5384 (2016)
Jiang, X., Lao, Q., Matwin, S., Havaei, M.: Implicit class-conditioned domain alignment for unsupervised domain adaptation. In: ICML, pp. 4816–4827. PMLR (2020)
Jin, X., Lan, C., Zeng, W., Chen, Z.: Re-energizing domain discriminator with sample relabeling for adversarial domain adaptation. In: ICCV (2021)
Jin, X., Lan, C., Zeng, W., Chen, Z.: Style normalization and restitution for domain generalization and adaptation. IEEE Trans. Multimedia 24, 3636–3651 (2021)
Johansson, F.D., Sontag, D., Ranganath, R.: Support and invertibility in domain-invariant representations. In: AISTATS, pp. 527–536. PMLR (2019)
Kang, B., et al.: Decoupling representation and classifier for long-tailed recognition. In: ICLR (2019)
Kang, G., Jiang, L., Yang, Y., Hauptmann, A.G.: Contrastive adaptation network for unsupervised domain adaptation. In: CVPR, pp. 4893–4902 (2019)
Kifer, D., Ben-David, S., Gehrke, J.: Detecting change in data streams. In: VLDB, vol. 4, pp. 180–191. Toronto, Canada (2004)
Li, B., et al.: Rethinking distributional matching based domain adaptation. arXiv preprint arXiv:2006.13352 (2020)
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)
Li, S., et al.: Semantic concentration for domain adaptation. In: ICCV, pp. 9102–9111 (2021)
Li, Y., et al.: Overcoming classifier imbalance for long-tail object detection with balanced group softmax. In: CVPR, pp. 10991–11000 (2020)
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)
Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: NeurIPS, pp. 1640–1650 (2018)
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: ICML, pp. 2208–2217 (2017)
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)
Luo, Y.W., Ren, C.X.: Conditional bures metric for domain adaptation. In: CVPR, pp. 13989–13998 (2021)
Nowozin, S., Cseke, B., Tomioka, R.: f-gan: training generative neural samplers using variational divergence minimization. In: NeurIPS (2016)
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019)
Pei, Z., Cao, Z., Long, M., Wang, J.: Multi-adversarial domain adaptation. In: AAAI, vol. 32 (2018)
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)
Peng, X., Usman, B., Kaushik, N., Hoffman, J., Wang, D., Saenko, K.: Visda: the visual domain adaptation challenge. arXiv preprint arXiv:1710.06924 (2017)
Peng, Z., Huang, W., Guo, Z., Zhang, X., Jiao, J., Ye, Q.: Long-tailed distribution adaptation. In: ACMMM, pp. 3275–3282 (2021)
Raab, C., Vath, P., Meier, P., Schleif, F.M.: Bridging adversarial and statistical domain transfer via spectral adaptation networks. In: ACCV (2020)
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
Saito, K., Kim, D., Sclaroff, S., Saenko, K.: Universal domain adaptation through self supervision. In: NeurIPS (2020)
Saito, K., Ushiku, Y., Harada, T., Saenko, K.: Strong-weak distribution alignment for adaptive object detection. In: CVPR, pp. 6956–6965 (2019)
Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: CVPR, pp. 3723–3732 (2018)
Sankaranarayanan, S., Balaji, Y., Castillo, C.D., Chellappa, R.: Generate to adapt: aligning domains using generative adversarial networks. In: CVPR, pp. 8503–8512 (2018)
Shimodaira, H.: Improving predictive inference under covariate shift by weighting the log-likelihood function. J. Stat. Plan. Inference 90(2), 227–244 (2000)
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)
Sugiyama, M., Krauledat, M., Müller, K.R.: Covariate shift adaptation by importance weighted cross validation. J. Mach. Learn. Res. 8(5), 1–21 (2007)
Sun, B., Feng, J., Saenko, K.: Return of frustratingly easy domain adaptation. In: AAAI, vol. 30 (2016)
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
Tang, H., Chen, K., Jia, K.: Unsupervised domain adaptation via structurally regularized deep clustering. In: CVPR, pp. 8725–8735 (2020)
Tang, H., Jia, K.: Discriminative adversarial domain adaptation. In: AAAI, vol. 34, pp. 5940–5947 (2020)
Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR 2011. pp. 1521–1528
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR, pp. 7167–7176 (2017)
Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: CVPR (2017)
Wang, S., Zhang, L.: Self-adaptive re-weighted adversarial domain adaptation. IJCAI (2020)
Wei, G., Lan, C., Zeng, W., Chen, Z.: Metaalign: coordinating domain alignment and classification for unsupervised domain adaptation. In: CVPR (2021)
Wu, Y., Donahue, J., Balduzzi, D., Simonyan, K., Lillicrap, T.: Logan: latent optimisation for generative adversarial networks. arXiv preprint arXiv:1912.00953 (2019)
Wu, Y., Winston, E., Kaushik, D., Lipton, Z.: Domain adaptation with asymmetrically-relaxed distribution alignment. In: ICML, pp. 6872–6881. PMLR (2019)
Xu, M., et al.: Adversarial domain adaptation with domain mixup. In: AAAI (2020)
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)
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
Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: NeurIPS (2014)
You, C., Li, C., Robinson, D.P., Vidal, R.: Scalable exemplar-based subspace clustering on class-imbalanced data. In: ECCV, pp. 67–83 (2018)
Zhang, J., Ding, Z., Li, W., Ogunbona, P.: Importance weighted adversarial nets for partial domain adaptation. In: CVPR, pp. 8156–8164 (2018)
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)
Zhang, Y., Tang, H., Jia, K., Tan, M.: Domain-symmetric networks for adversarial domain adaptation. In: CVPR, pp. 5031–5040 (2019)
Zhang, Y., Liu, T., Long, M., Jordan, M.I.: Bridging theory and algorithm for domain adaptation. In: ICML (2019)
Zhao, H., Des Combes, R.T., Zhang, K., Gordon, G.: On learning invariant representations for domain adaptation. In: ICML, pp. 7523–7532. PMLR (2019)
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)
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)
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
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
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)