Yan, Zizheng, Wu, Yushuang, Qin, Yipeng  ORCID: https://orcid.org/0000-0002-1551-9126, Han, Xiaoguang, Cui, Shuguang and Li, Guanbin
2024.
Universal semi-supervised model adaptation via collaborative consistency training.
Presented at: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2024),
Waikoloa, Hawaii, United States,
4 - 8 January 2024.
2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
IEEE,
pp. 861-871.
10.1109/WACV57701.2024.00092
|
Preview |
PDF
- Accepted Post-Print Version
Download (1MB) | Preview |
Abstract
In this paper, we introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA), which i) requires only a pre-trained source model, ii) allows the source and target domain to have different label sets, i.e., they share a common label set and hold their own private label set, and iii) requires only a few labeled samples in each class of the target domain. To address USMA, we propose a collaborative consistency training framework that regularizes the prediction consistency between two models, i.e., a pre-trained source model and its variant pre-trained with target data only, and combines their complementary strengths to learn a more powerful model. The rationale of our framework stems from the observation that the source model performs better on common categories than the target-only model, while on target-private categories, the target-only model performs better. We also propose a two-perspective, i.e., sample-wise and class-wise, consistency regularization to improve the training. Experimental results demonstrate the effectiveness of our method on several benchmark datasets.
| Item Type: | Conference or Workshop Item - published (Paper) |
|---|---|
| Date Type: | Publication |
| Status: | Published |
| Schools: | Schools > Computer Science & Informatics |
| Publisher: | IEEE |
| ISBN: | 979-8-3503-1893-7 |
| ISSN: | 2472-6737 |
| Date of First Compliant Deposit: | 16 April 2026 |
| Date of Acceptance: | 24 October 2023 |
| Last Modified: | 16 Apr 2026 09:30 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/163691 |
Actions (repository staff only)
 |
Edit Item |
Dimensions
Dimensions