{"ID":2863682,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24896","arxiv_id":"2509.24896","title":"DAM: Dual Active Learning with Multimodal Foundation Model for Source-Free Domain Adaptation","abstract":"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.","short_abstract":"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 alignmen...","url_abs":"https://arxiv.org/abs/2509.24896","url_pdf":"https://arxiv.org/pdf/2509.24896v1","authors":"[\"Xi Chen\",\"Hongxun Yao\",\"Zhaopan Xu\",\"Kui Jiang\"]","published":"2025-09-29T15:06:56Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}