Enhanced hard negative synthesis for contrastive learning in skin lesion classification

Xue Zhang; Kaida Jiang; Li Quan; Tao Gong

doi:10.1117/12.3039105

13 September 2024 Enhanced hard negative synthesis for contrastive learning in skin lesion classification

Xue Zhang, Kaida Jiang, Li Quan, Tao Gong

Proceedings Volume 13254, Fourth International Conference on Optics and Image Processing (ICOIP 2024); 132541V (2024) https://doi.org/10.1117/12.3039105
Event: Fourth International Conference on Optics and Image Processing (ICOIP 2024), 2024, Chongqing, China

Abstract

The analysis of skin lesion dermoscopic images has traditionally relied on supervised learning paradigms, necessitating extensive labeled datasets which can be costly and time-consuming for dermatologists. Conversely, the abundance of unlabeled data offers a promising avenue for self-supervised learning methods in this field. In this work, we introduce a novel strategy for hard negative synthesis that bolsters the efficacy of contrastive learning in skin lesion classification. By strategically down-weighting the contribution of the hardest negative samples during feature-level mixing, our method ensures the neural network prioritizes learning from the most informative and reliable negatives, thereby enhancing the model's feature learning ability. After fine-tuning with a limited set of labeled data, our method demonstrates notable superiority on the ISIC-2016 classification dataset, achieving a 4.29% increase in ROC AUC and a 5.39% increase in F1 score over the standard MoCo-v2 framework.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Xue Zhang, Kaida Jiang, Li Quan, and Tao Gong "Enhanced hard negative synthesis for contrastive learning in skin lesion classification", Proc. SPIE 13254, Fourth International Conference on Optics and Image Processing (ICOIP 2024), 132541V (13 September 2024); https://doi.org/10.1117/12.3039105

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available