闭合困惑循环：CLIP引导的源无关领域适应对齐
Closing the Confusion Loop: CLIP-Guided Alignment for Source-Free Domain Adaptation
AI总结：
CLIP引导的对齐框架通过建模和缓解类别混淆，提升源无关领域适应的性能，尤其在细粒度场景中表现突出。
摘要：
源无关领域适应（SFDA）旨在在不访问任何源数据的情况下，将预训练的源模型适应到无标签的目标领域，这在数据安全领域非常适用。尽管最近的进展表明伪标签策略可以有效，但它们在细粒度场景中往往因微妙的类间相似性而失败。一个关键但尚未深入研究的问题是存在不对称和动态的类别混淆，其中视觉相似的类别被源模型不均且不一致地误分类。现有方法通常忽略此类混淆模式，导致噪声的伪标签和较差的目标辨别能力。为了解决这一问题，我们提出了CLIP引导的对齐（CGA），一种新的框架，明确建模并缓解SFDA中的类别混淆。一般来说，我们的方法由三部分组成：（1）MCA：通过分析源模型在目标领域的预测来检测第一方向的混淆对；（2）MCC：利用CLIP构建具有混淆意识的文本提示（例如，看起来像巴士的卡车），从而实现更具上下文敏感性的伪标签；（3）FAM：为CLIP和源模型构建具有混淆引导的特征库，并利用对比学习对齐它们以减少表示空间中的歧义。在各种数据集上的广泛实验表明，CGA在各种数据集上始终优于最先进的SFDA方法，尤其在易混淆和细粒度场景中表现显著。我们的结果突显了明确建模类间混淆对于有效源无关适应的重要性。我们的代码可在https://github.com/soloiro/CGA找到。
英文摘要：
Source-Free Domain Adaptation (SFDA) tackles the problem of adapting a pre-trained source model to an unlabeled target domain without accessing any source data, which is quite suitable for the field of data security. Although recent advances have shown that pseudo-labeling strategies can be effective, they often fail in fine-grained scenarios due to subtle inter-class similarities. A critical but underexplored issue is the presence of asymmetric and dynamic class confusion, where visually similar classes are unequally and inconsistently misclassified by the source model. Existing methods typically ignore such confusion patterns, leading to noisy pseudo-labels and poor target discrimination. To address this, we propose CLIP-Guided Alignment(CGA), a novel framework that explicitly models and mitigates class confusion in SFDA. Generally, our method consists of three parts: (1) MCA: detects first directional confusion pairs by analyzing the predictions of the source model in the target domain; (2) MCC: leverages CLIP to construct confusion-aware textual prompts (e.g. a truck that looks like a bus), enabling more context-sensitive pseudo-labeling; and (3) FAM: builds confusion-guided feature banks for both CLIP and the source model and aligns them using contrastive learning to reduce ambiguity in the representation space. Extensive experiments on various datasets demonstrate that CGA consistently outperforms state-of-the-art SFDA methods, with especially notable gains in confusion-prone and fine-grained scenarios. Our results highlight the importance of explicitly modeling inter-class confusion for effective source-free adaptation. Our code can be find at https://github.com/soloiro/CGA
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
