Few-shot Class-incremental Learning for Cross-domain Disease Classification

04/12/2023
by   Hao Yang, et al.
0

The ability to incrementally learn new classes from limited samples is crucial to the development of artificial intelligence systems for real clinical application. Although existing incremental learning techniques have attempted to address this issue, they still struggle with only few labeled data, particularly when the samples are from varied domains. In this paper, we explore the cross-domain few-shot incremental learning (CDFSCIL) problem. CDFSCIL requires models to learn new classes from very few labeled samples incrementally, and the new classes may be vastly different from the target space. To counteract this difficulty, we propose a cross-domain enhancement constraint and cross-domain data augmentation method. Experiments on MedMNIST show that the classification performance of this method is better than other similar incremental learning methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/23/2020

Few-Shot Class-Incremental Learning

The ability to incrementally learn new classes is crucial to the develop...
research
04/24/2021

Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System

Text classification is usually studied by labeling natural language text...
research
07/30/2022

Few-Shot Class-Incremental Learning from an Open-Set Perspective

The continual appearance of new objects in the visual world poses consid...
research
03/16/2023

A Survey of Deep Visual Cross-Domain Few-Shot Learning

Few-Shot transfer learning has become a major focus of research as it al...
research
11/17/2016

Cross-Domain Face Verification: Matching ID Document and Self-Portrait Photographs

Cross-domain biometrics has been emerging as a new necessity, which pose...
research
10/04/2018

Transfer Incremental Learning using Data Augmentation

Deep learning-based methods have reached state of the art performances, ...
research
08/08/2023

SoK: Cross-Domain MEV

We examine the current state of the cross-domain world, with particular ...

Please sign up or login with your details

Forgot password? Click here to reset