Multi-level consistency learning for semi-supervised domain adaptation

Yan, Zizheng, Wu, Yushuang, Li, Guanbin, Qin, Yipeng ORCID: https://orcid.org/0000-0002-1551-9126, Han, Xiaoguang and Cui, Shuguang 2022. Multi-level consistency learning for semi-supervised domain adaptation. Presented at: 31st International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2022), Vienna, Austria, 23-29 July 2022. Published in: De Raedt, Lud ed. Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence Organization, pp. 1530-1536. 10.24963/ijcai.2022/213

Preview

PDF - Accepted Post-Print Version Download (996kB) | Preview

Abstract

Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned from a fully labeled source domain to a scarcely labeled target domain. In this paper, we propose a Multi-level Consistency Learning (MCL) framework for SSDA. Specifically, our MCL regularizes the consistency of different views of target domain samples at three levels: (i) at inter-domain level, we robustly and accurately align the source and target domains using a prototype-based optimal transport method that utilizes the pros and cons of different views of target samples; (ii) at intra-domain level, we facilitate the learning of both discriminative and compact target feature representations by proposing a novel class-wise contrastive clustering loss; (iii) at sample level, we follow standard practice and improve the prediction accuracy by conducting a consistency-based self-training. Empirically, we verified the effectiveness of our MCL framework on three popular SSDA benchmarks, i.e., VisDA2017, DomainNet, and Office-Home datasets, and the experimental results demonstrate that our MCL framework achieves the state-of-the-art performance.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	International Joint Conferences on Artificial Intelligence Organization
Date of First Compliant Deposit:	9 May 2022
Date of Acceptance:	20 April 2022
Last Modified:	03 Jul 2025 14:22
URI:	https://orca.cardiff.ac.uk/id/eprint/149471

Actions (repository staff only)

Edit Item