Abstract
The main goal of unsupervised domain adaptation is to improve the classification performance on unlabeled data in target domains. Many methods try to reduce the domain gap by treating multiple domains as one to enhance the generalization of a model. However, aligning domains as a whole does not account for instance-level alignment, which might lead to sub-optimal results. Currently, many researchers utilize meta-learning and instance segmentation approaches to tackle this problem. But it can only obtain a further optimized the domain-invariant feature learned by the model, rather than achieve instance-level alignment. In this paper, we interpret unsupervised domain adaptation from a new perspective, which exploits the energy difference between the source and target domains to reduce the performance drops caused by the domain gap. At the same time, we improve and exploit the contrastive learning loss, which can push the target domain away from the decision boundary. The experimental results on different benchmarks against a range of the state-of-the-art approaches justify the performance and the effectiveness of the proposed method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: PMLR, pp. 97–105 (2015)
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: PMLR, pp. 2208–2217 (2017)
Kang, G., Zheng, L., Yan, Y., Yang, Y.: Deep adversarial attention alignment for unsupervised domain adaptation: the benefit of target expectation maximization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 420–436. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01252-6_25
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: PMLR, pp. 1180–1189 (2015)
Hoffman, J., et al.: Cycada: cycle-consistent adversarial domain adaptation. In: ICML. PMLR, pp. 1989–1998 (2018)
Shao, H., Yuan, Z., Peng, X., Wu, X.: Contrastive learning in frequency domain for non-i.I.D. image classification. In: International Conference on Multimedia Modeling (2021)
Cui, S., Jin, X., Wang, S., He, Y., Huang, Q.: Heuristic domain adaptation. In: NeurlPS vol. 33, pp. 7571–7583 (2020)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: PMLR, vol. 10, pp. 1597–1607 (2020)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9729–9738 (2020)
Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: CVPR, pp. 5018–5027 (2017)
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
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: CVPR, pp. 3723–3732 (2018)
Zhang, Y., Liu, T., Long, M., Jordan, M.: Bridging theory and algorithm for domain adaptation. In: ICML. PMLR, pp. 7404–7413 (2019)
Ben-David, S., Blitzer, J., Crammer, K., Pereira, F.: Analysis of representations for domain adaptation. In: NeurlPS, vol. 19 (2006)
Chen, Y.-C., Gao, C., Robb, E., Huang, J.-B.: NAS-DIP: learning deep image prior with neural architecture search. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 442–459. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58523-5_26
Saito, K., Saenko, K.: OVANet:: one-vs-all network for universal domain adaptation. In: ICCV, pp. 9000–9009 (2021)
Singh, A.: CLDA: contrastive learning for semi-supervised domain adaptation. In: NerulPS, vol. 34 (2021)
Cui, S., Wang, S., Zhuo, J., Su, C., Huang, Q., Tian, Q.: Gradually vanishing bridge for adversarial domain adaptation. In: CVPR, pp. 12 455–12 464 (2020)
Hu, L., Kan, M., Shan, S., Chen, X.: Unsupervised domain adaptation with hierarchical gradient synchronization. In: CVPR, pp. 4043–4052 (2020)
Wei, G., Lan, C., Zeng, W., Chen, Z.: Metaalign: coordinating domain alignment and classification for unsupervised domain adaptation. In: CVPR, pp. 16 643–16 653 (2021)
James, S., et al.: Sim-to-real via sim-to-sim: data-efficient robotic grasping via randomized-to-canonical adaptation networks. In: CVPR, pp. 12 627–12 637 (2019)
Wang, Y., et al.: Clusterscl: cluster-aware supervised contrastive learning on graphs. In: Proceedings of the ACM Web Conference 2022, 1611–1621 (2022)
Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)
Goodfellow, I.J., et al.: Generative adversarial nets. In: NeurIPS (2014)
Kang, G., Jiang, L., Yang, Y., Hauptmann, A.G.: Contrastive adaptation network for unsupervised domain adaptation. In: ICCV, pp. 4893–4902 (2019)
Zhong, H., et al.: Graph contrastive clustering. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9224–9233 (2021)
Liu, W., Wang, X., Owens, J., Li, Y.: Energy-based out-of-distribution detection. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21 464–21 475 (2020)
LeCun, Y., Chopra, S., Hadsell, R., Ranzato, M., Huang, F.: A tutorial on energy-based learning. In: Predicting Structured Data, vol. 1, no. 0 (2006)
Wang, Y., et al.: Revisiting the transferability of supervised pretraining: an MLP perspective. arXiv preprint arXiv:2112.00496 (2021)
Li, Y., Hu, P., Liu, Z., Peng, D., Zhou, J.T., Peng, X.: Contrastive clustering. In: Proceedings of the AAAI Conference on Artificial Intelligence 35(10), 8547–8555 (2021)
Gao, Y., Chaudhari, P.: A free-energy principle for representation learning. In: International Conference on Machine Learning. PMLR, pp. 3367–3376 (2020)
Vu, T.-H., Jain, H., Bucher, M., Cord, M., Pérez, P.: Advent: adversarial entropy minimization for domain adaptation in semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2517–2526 (2019)
Deng, J., et al.:ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248–255 (2009)
Wang, F., Ding, Y., Liang, H., Wen, J.: Discriminative and selective pseudo-labeling for domain adaptation. In: International Conference on Multimedia Modeling (2021)
Acknowledgement
This work was supported by the Natural Science Foundation of China under Grant 41906177 and 41927805, the Hainan Provincial Joint Project of Sanya Yazhou Bay Science and Technology City under Grants 2021JJLH0061, The National Key Research and Development Program of China under Grants 2018AAA0100605.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ouyang, J., Lv, Q., Zhang, S., Dong, J. (2023). Energy Transfer Contrast Network for Unsupervised Domain Adaption. In: Dang-Nguyen, DT., et al. MultiMedia Modeling. MMM 2023. Lecture Notes in Computer Science, vol 13834. Springer, Cham. https://doi.org/10.1007/978-3-031-27818-1_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-27818-1_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-27817-4
Online ISBN: 978-3-031-27818-1
eBook Packages: Computer ScienceComputer Science (R0)