2020/04/21 by Wei Zhu, Haofu Liao, Zhu, Wei +7
Medicine · #Computer Vision and Pattern Recognition (cs.CV) #Cutaneous Melanoma Detection and Management #Dermatological and COVID-19 studies #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Systemic Lupus Erythematosus Research #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2004.09694
openalex publication_date 2020/04/21 · openalex created_date 2020/05/01 · openalex updated_date 2026/07/28
Skin disease classification from images is crucial to dermatological diagnosis. However, identifying skin lesions involves a variety of aspects in terms of size, color, shape, and texture. To make matters worse, many categories only contain very few samples, posing great challenges to conventional machine learning algorithms and even human experts. Inspired by the recent success of Few-Shot Learning (FSL) in natural image classification, we propose to apply FSL to skin disease identification to address the extreme scarcity of training sample problem. However, directly applying FSL to this task does not work well in practice, and we find that the problem can be largely attributed to the incompatibility between Cross Entropy (CE) and episode training, which are both commonly used in FSL. Based on a detailed analysis, we propose the Query-Relative (QR) loss, which proves superior to CE under episode training and is closely related to recently proposed mutual information estimation. Moreover, we further strengthen the proposed QR loss with a novel adaptive hard margin strategy. Comprehensive experiments validate the effectiveness of the proposed FSL scheme and the possibility to diagnosis rare skin disease with a few labeled samples.