{"ID":5551904,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T01:45:22.703757252Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00369","arxiv_id":"2607.00369","title":"SFDATrack: Generalized Source-Free Domain Adaptive Tracking Under Adverse Weather Conditions","abstract":"Domain adaptive visual object tracking under adverse weather conditions has garnered significant attention in recent years. Despite the impressive performance, existing methods heavily rely on the large-scale video frames from both source and target domains, which is impractical under rigid resource constraints where source data is unavailable. To overcome this limitation, we propose SFDATrack, a generalized source-free domain adaptive tracker that merely leverages adverse weather samples from the target domain for robust state estimation. Specifically, SFDATrack first employs a mean-teacher backbone with Dual Interactive Mamba (DIM) blocks to distill the candidate target tokens that are resilient to weather variations from classified, augmented samples. Afterwards, we introduce a hyperspherical prototype projection (HPP) module to project these tokens onto multi-domain prototypes within a latent hyperspherical space. By enforcing both domain-specific and domain-invariant properties of the multi-domain prototypes, SFDATrack can be seamlessly adapted to diverse weather conditions with powerful generalizability. Extensive experiments evaluated on various benchmarks demonstrate that SFDATrack achieves superior performance compared to state-of-the-art approaches. The code is available at https://github.com/watcherBR0/sfdatrack.","short_abstract":"Domain adaptive visual object tracking under adverse weather conditions has garnered significant attention in recent years. Despite the impressive performance, existing methods heavily rely on the large-scale video frames from both source and target domains, which is impractical under rigid resource constraints where s...","url_abs":"https://arxiv.org/abs/2607.00369","url_pdf":"https://arxiv.org/pdf/2607.00369v1","authors":"[\"Siyuan Yao\",\"Ziqi Wang\",\"Ruiqi Yu\",\"Junqi Huang\",\"Wenqi Ren\",\"Xiaochun Cao\"]","published":"2026-07-01T03:09:12Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":613851,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-02T01:54:51.863792489Z","DeletedAt":null,"paper_id":5551904,"paper_url":"https://arxiv.org/abs/2607.00369","paper_title":"SFDATrack: Generalized Source-Free Domain Adaptive Tracking Under Adverse Weather Conditions","repo_url":"https://github.com/watcherBR0/sfdatrack","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}