发表机构
Shenzhen Campus of Sun Yat-sen University; Beijing University of Posts and Telecommunications; Nanyang Technological University（中山大学深圳校区; 北京邮电大学; 南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出SFDATrack，一种仅利用目标域恶劣天气样本的无源域自适应跟踪器，通过双交互Mamba骨干和超球原型投影实现鲁棒状态估计，在多个基准上超越现有方法。
AI 中文摘要
近年来，恶劣天气条件下的域自适应视觉目标跟踪引起了广泛关注。尽管现有方法性能出色，但它们严重依赖于来自源域和目标域的大规模视频帧，这在源数据不可用的严格资源约束下是不切实际的。为了克服这一限制，我们提出了SFDATrack，一种广义的无源域自适应跟踪器，仅利用来自目标域的恶劣天气样本进行鲁棒状态估计。具体来说，SFDATrack首先采用带有双交互Mamba（DIM）块的均值教师骨干，从分类和增强样本中提取对天气变化具有鲁棒性的候选目标令牌。然后，我们引入超球原型投影（HPP）模块，将这些令牌投影到潜在超球空间中的多域原型上。通过强制多域原型的域特定和域不变特性，SFDATrack可以无缝适应各种天气条件，并具有强大的泛化能力。在多个基准上的大量实验表明，SFDATrack的性能优于最先进的方法。代码可在以下网址获取：https://this URL。
英文摘要
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.
CommentsAccepted to ECCV 2026
