FunOTTA: On-the-Fly Adaptation on Cross-Domain Fundus Image via Stable Test-time Training
This work addresses domain adaptation for fundus image diagnosis, which is crucial for deploying AI models in real-world medical settings, but it appears incremental as it builds on existing test-time adaptation pipelines.
The authors tackled the problem of domain shifts in fundus images from different devices and locations by proposing FunOTTA, a test-time adaptation framework that generalizes diagnosis models to unseen environments, achieving superior performance compared to state-of-the-art methods on cross-domain benchmarks for two eye diseases.
Fundus images are essential for the early screening and detection of eye diseases. While deep learning models using fundus images have significantly advanced the diagnosis of multiple eye diseases, variations in images from different imaging devices and locations (known as domain shifts) pose challenges for deploying pre-trained models in real-world applications. To address this, we propose a novel Fundus On-the-fly Test-Time Adaptation (FunOTTA) framework that effectively generalizes a fundus image diagnosis model to unseen environments, even under strong domain shifts. FunOTTA stands out for its stable adaptation process by performing dynamic disambiguation in the memory bank while minimizing harmful prior knowledge bias. We also introduce a new training objective during adaptation that enables the classifier to incrementally adapt to target patterns with reliable class conditional estimation and consistency regularization. We compare our method with several state-of-the-art test-time adaptation (TTA) pipelines. Experiments on cross-domain fundus image benchmarks across two diseases demonstrate the superiority of the overall framework and individual components under different backbone networks. Code is available at https://github.com/Casperqian/FunOTTA.