A Tale of Two Experts: Cooperative Learning for Source-Free Unsupervised Domain Adaptation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911193788055552 |
|---|---|
| author | Yu, Jiaping Yang, Muli Ji, Jiapeng Yan, Jiexi Deng, Cheng |
| author_facet | Yu, Jiaping Yang, Muli Ji, Jiapeng Yan, Jiexi Deng, Cheng |
| contents | Source-Free Unsupervised Domain Adaptation (SFUDA) addresses the realistic challenge of adapting a source-trained model to a target domain without access to the source data, driven by concerns over privacy and cost. Existing SFUDA methods either exploit only the source model's predictions or fine-tune large multimodal models, yet both neglect complementary insights and the latent structure of target data. In this paper, we propose the Experts Cooperative Learning (EXCL). EXCL contains the Dual Experts framework and Retrieval-Augmentation-Interaction optimization pipeline. The Dual Experts framework places a frozen source-domain model (augmented with Conv-Adapter) and a pretrained vision-language model (with a trainable text prompt) on equal footing to mine consensus knowledge from unlabeled target samples. To effectively train these plug-in modules under purely unsupervised conditions, we introduce Retrieval-Augmented-Interaction(RAIN), a three-stage pipeline that (1) collaboratively retrieves pseudo-source and complex target samples, (2) separately fine-tunes each expert on its respective sample set, and (3) enforces learning object consistency via a shared learning result. Extensive experiments on four benchmark datasets demonstrate that our approach matches state-of-the-art performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22229 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Tale of Two Experts: Cooperative Learning for Source-Free Unsupervised Domain Adaptation Yu, Jiaping Yang, Muli Ji, Jiapeng Yan, Jiexi Deng, Cheng Computer Vision and Pattern Recognition Source-Free Unsupervised Domain Adaptation (SFUDA) addresses the realistic challenge of adapting a source-trained model to a target domain without access to the source data, driven by concerns over privacy and cost. Existing SFUDA methods either exploit only the source model's predictions or fine-tune large multimodal models, yet both neglect complementary insights and the latent structure of target data. In this paper, we propose the Experts Cooperative Learning (EXCL). EXCL contains the Dual Experts framework and Retrieval-Augmentation-Interaction optimization pipeline. The Dual Experts framework places a frozen source-domain model (augmented with Conv-Adapter) and a pretrained vision-language model (with a trainable text prompt) on equal footing to mine consensus knowledge from unlabeled target samples. To effectively train these plug-in modules under purely unsupervised conditions, we introduce Retrieval-Augmented-Interaction(RAIN), a three-stage pipeline that (1) collaboratively retrieves pseudo-source and complex target samples, (2) separately fine-tunes each expert on its respective sample set, and (3) enforces learning object consistency via a shared learning result. Extensive experiments on four benchmark datasets demonstrate that our approach matches state-of-the-art performance. |
| title | A Tale of Two Experts: Cooperative Learning for Source-Free Unsupervised Domain Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.22229 |