Closing the Confusion Loop: CLIP-Guided Alignment for Source-Free Domain Adaptation

TL;DR

This paper introduces CLIP-Guided Alignment, a novel framework for source-free domain adaptation that explicitly models and mitigates class confusion, leading to improved performance especially in fine-grained scenarios.

Contribution

The paper proposes a new framework that detects class confusion, uses CLIP for context-aware pseudo-labeling, and aligns feature representations to enhance source-free domain adaptation.

Findings

Outperforms state-of-the-art SFDA methods on various datasets.

Achieves significant gains in confusion-prone and fine-grained scenarios.

Highlights the importance of modeling inter-class confusion for effective adaptation.

Abstract

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