DAM: Dual Active Learning with Multimodal Foundation Model for Source-Free Domain Adaptation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915522195488768 |
|---|---|
| author | Chen, Xi Yao, Hongxun Xu, Zhaopan Jiang, Kui |
| author_facet | Chen, Xi Yao, Hongxun Xu, Zhaopan Jiang, Kui |
| contents | Source-free active domain adaptation (SFADA) enhances knowledge transfer from a source model to an unlabeled target domain using limited manual labels selected via active learning. While recent domain adaptation studies have introduced Vision-and-Language (ViL) models to improve pseudo-label quality or feature alignment, they often treat ViL-based and data supervision as separate sources, lacking effective fusion. To overcome this limitation, we propose Dual Active learning with Multimodal (DAM) foundation model, a novel framework that integrates multimodal supervision from a ViL model to complement sparse human annotations, thereby forming a dual supervisory signal. DAM initializes stable ViL-guided targets and employs a bidirectional distillation mechanism to foster mutual knowledge exchange between the target model and the dual supervisions during iterative adaptation. Extensive experiments demonstrate that DAM consistently outperforms existing methods and sets a new state-of-the-art across multiple SFADA benchmarks and active learning strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24896 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DAM: Dual Active Learning with Multimodal Foundation Model for Source-Free Domain Adaptation Chen, Xi Yao, Hongxun Xu, Zhaopan Jiang, Kui Computer Vision and Pattern Recognition Source-free active domain adaptation (SFADA) enhances knowledge transfer from a source model to an unlabeled target domain using limited manual labels selected via active learning. While recent domain adaptation studies have introduced Vision-and-Language (ViL) models to improve pseudo-label quality or feature alignment, they often treat ViL-based and data supervision as separate sources, lacking effective fusion. To overcome this limitation, we propose Dual Active learning with Multimodal (DAM) foundation model, a novel framework that integrates multimodal supervision from a ViL model to complement sparse human annotations, thereby forming a dual supervisory signal. DAM initializes stable ViL-guided targets and employs a bidirectional distillation mechanism to foster mutual knowledge exchange between the target model and the dual supervisions during iterative adaptation. Extensive experiments demonstrate that DAM consistently outperforms existing methods and sets a new state-of-the-art across multiple SFADA benchmarks and active learning strategies. |
| title | DAM: Dual Active Learning with Multimodal Foundation Model for Source-Free Domain Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.24896 |