# Alleviating the Incompatibility between Cross Entropy Loss and Episode Training for Few-shot Skin Disease Classification

arXiv: https://arxiv.org/abs/2004.09694 · HTML: https://mlsanity.com/paper/2004.09694/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2020.

## Built on by (most cited first, 7 of 7)

- [A Systematic Review of Few-Shot Learning in Medical Imaging](https://mlsanity.com/paper/2309.11433/) (2023)
- [Personalized Retrogress-Resilient Framework for Real-World Medical Federated Learning](https://mlsanity.com/paper/2110.00394/) (2021)
- [Data efficient deep learning for medical image analysis: A survey](https://mlsanity.com/paper/2310.06557/) (2023)
- [Unsupervised Representation Learning Meets Pseudo-Label Supervised Self-Distillation: A New Approach to Rare Disease Classification](https://mlsanity.com/paper/2110.04558/) (2021)
- [SegPrompt: Using Segmentation Map as a Better Prompt to Finetune Deep Models for Kidney Stone Classification](https://mlsanity.com/paper/2303.08303/) (2023)
- [Dynamic Sub-Cluster-Aware Network for Few-Shot Skin Disease Classification](https://mlsanity.com/paper/2207.01072/) (2022)
- [Meta-Transfer Derm-Diagnosis: Exploring Few-Shot Learning and Transfer Learning for Skin Disease Classification in Long-Tail Distribution](https://mlsanity.com/paper/2404.16814/) (2024)

## Abstract (arXiv)

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.