Forgetting-Resistant and Lesion-Aware Source-Free Domain Adaptive Fundus Image Analysis with Vision-Language Model

TL;DR

This paper proposes a novel forgetting-resistant and lesion-aware method for source-free domain adaptation in fundus image analysis, leveraging vision-language models to improve accuracy and lesion localization under domain shift.

Contribution

It introduces a new FRLA approach that preserves confident predictions and utilizes ViL models' detailed knowledge, addressing forgetting and enhancing lesion awareness.

Findings

Significantly outperforms existing methods.

Achieves consistent improvements over state-of-the-art.

Effectively preserves confident predictions during adaptation.

Abstract

Source-free domain adaptation (SFDA) aims to adapt a model trained in the source domain to perform well in the target domain, with only unlabeled target domain data and the source model. Taking into account that conventional SFDA methods are inevitably error-prone under domain shift, recently greater attention has been directed to SFDA assisted with off-the-shelf foundation models, e.g., vision-language (ViL) models. However, existing works of leveraging ViL models for SFDA confront two issues: (i) Although mutual information is exploited to consider the joint distribution between the predictions of ViL model and the target model, we argue that the forgetting of some superior predictions of the target model still occurs, as indicated by the decline of the accuracies of certain classes during adaptation; (ii) Prior research disregards the rich, fine-grained knowledge embedded in the ViL model, which offers detailed grounding for fundus image diagnosis. In this paper, we introduce a novel forgetting-resistant and lesion-aware (FRLA) method for SFDA of fundus image diagnosis with ViL model. Specifically, a forgetting-resistant adaptation module explicitly preserves the confident predictions of the target model, and a lesion-aware adaptation module yields patch-wise predictions from ViL model and employs them to help the target model be aware of the lesion areas and leverage the ViL model's fine-grained knowledge. Extensive experiments show that our method not only significantly outperforms the vision-language model, but also achieves consistent improvements over the state-of-the-art methods. Our code will be released.