FunOTTA: On-the-Fly Adaptation on Cross-Domain Fundus Image via Stable Test-time Training

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zeng, Qian, Zhang, Le, Liu, Yipeng, Zhu, Ce, Zhang, Fan
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911252243021824
author Zeng, Qian
Zhang, Le
Liu, Yipeng
Zhu, Ce
Zhang, Fan
author_facet Zeng, Qian
Zhang, Le
Liu, Yipeng
Zhu, Ce
Zhang, Fan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_04396
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FunOTTA: On-the-Fly Adaptation on Cross-Domain Fundus Image via Stable Test-time Training
Zeng, Qian
Zhang, Le
Liu, Yipeng
Zhu, Ce
Zhang, Fan
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title FunOTTA: On-the-Fly Adaptation on Cross-Domain Fundus Image via Stable Test-time Training
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2407.04396