Abstract
Multi-source domain adaptation aims to leverage multiple labeled source domains to train a classifier for an unlabeled target domain. Existing methods address the domain discrepancy by learning the invariant representation. However, due to the large difference in image style, image occlusion and missing, etc., the invariant representation tends to be inadequate, and some components tend to be lost. To this end, a multi-source domain adaptation method with multi-modal representation for components is proposed. It learns the multi-modal representation for missing components from an external knowledge graph. First, the semantic representation of the class subgraph, including not only the class but also rich class components, is learned from knowledge graph. Second, the semantic representation is fused with the visual representations of each domain respectively. Finally, the multi-modal invariant representations of source and target domains are learned. Experiments show the effectiveness of our method.
Supported by the National Natural Science Foundation of China under grant 61976077, the Natural Science Foundation of Anhui Province under grant 2208085MF170 and the University Synergy Innovation Program of Anhui Province under grant GXXT-2022-040.
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
Zuo, Y., Yao, H., Xu, C.: Attention-based multi-source domain adaptation. IEEE Trans. Image Process. 30, 3793–3803 (2021)
Kang, G., Jiang, L., Wei, Y., Yang, Y., Hauptmann, A.: Contrastive adaptation network for single- and multi-source domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell. 44 1793–1804 (2022)
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)
Deng, Z., Zhou, K., Yang, Y., Xiang, T.: Domain attention consistency for multi-source domain adaptation. In: BMVC, p. 4 (2021)
Wang, H., Xu, M., Ni, B., Zhang, W.: Learning to Combine: Knowledge Aggregation for Multi-source Domain Adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 727–744. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58598-3_43
Speer, R., Chin, J., Havasi, C.: Conceptnet 5.5: an open multilingual graph of general knowledge. In: AAAI, pp. 4444–4451 (2017)
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP, pp. 1532–1543 (2014)
Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: CVPR, pp. 5385–5394 (2017)
Long, M., Cao, Y., Wang, J., Jordan, M. I.: Learning transferable features with deep adaptation networks. In: ICML, pp. 97–105 (2015)
Ganin, Y.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17, 1–35 (2016)
Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: CVPR, pp. 3723–3732 (2018)
Li, Y., Yuan, L., Chen, Y., Wang, P., Vasconcelos, N.: Dynamic transfer for multi-source domain adaptation. In: CVPR, pp. 10998–11007 (2021)
Wang, Z., Zhou, C., Du, B., He, F.: Self-paced supervision for multi-source domain adaptation. In: Raedt, L.D. (eds)., IJCAI, pp. 3551–3557 (2022)
Dong, J., Fang, Z., Liu, A., Sun, G., Liu, T.: Confident anchor-induced multi-source free domain adaptation. In: NeurIPS, pp. 2848–2860 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, Y., Lin, Z., Qian, L., Hu, X. (2024). Multi-modal Component Representation for Multi-source Domain Adaptation Method. In: Liu, F., Sadanandan, A.A., Pham, D.N., Mursanto, P., Lukose, D. (eds) PRICAI 2023: Trends in Artificial Intelligence. PRICAI 2023. Lecture Notes in Computer Science(), vol 14325. Springer, Singapore. https://doi.org/10.1007/978-981-99-7019-3_11
Download citation
DOI: https://doi.org/10.1007/978-981-99-7019-3_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7018-6
Online ISBN: 978-981-99-7019-3
eBook Packages: Computer ScienceComputer Science (R0)