Few-shot Class-incremental Learning for Retinal Disease Recognition.
IEEE J Biomed Health Inform
; PP2024 Sep 18.
Article
em En
| MEDLINE
| ID: mdl-39292587
ABSTRACT
Few-Shot Class-Incremental Learning (FSCIL) techniques are essential for developing Deep Learning (DL) models that can continuously learn new classes with limited samples while retaining existing knowledge. This capability is particularly crucial for DL-based retinal disease diagnosis system, where acquiring large annotated datasets is challenging, and disease phenotypes evolve over time. This paper introduces Re-FSCIL, a novel framework for Few-Shot Class-Incremental Retinal Disease Recognition (FSCIRDR). Re-FSCIL integrates the RETFound model with a fine-grained module, employing a forward-compatible training strategy to improve adaptability, supervised contrastive learning to enhance feature discrimination, and feature fusion for robust representation quality. We convert existing datasets into the FSCIL format and reproduce numerous representative FSCIL methods to create two new benchmarks, RFMiD38 and JSIEC39, specifically for FSCIRDR. Our experimental results demonstrate that Re-FSCIL achieves State-of-the-art (SOTA) performance, significantly surpassing existing FSCIL methods on these benchmarks.
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Idioma:
En
Revista:
IEEE J Biomed Health Inform
Ano de publicação:
2024
Tipo de documento:
Article
País de publicação:
Estados Unidos