Research Article
A Survey on Meta-learning Based Few-Shot Classification
@INPROCEEDINGS{10.1007/978-3-031-04409-0_23, author={Weizhi Huang and Ming He and Yongle Wang}, title={A Survey on Meta-learning Based Few-Shot Classification}, proceedings={Machine Learning and Intelligent Communications. 6th EAI International Conference, MLICOM 2021, Virtual Event, November 2021, Proceedings}, proceedings_a={MLICOM}, year={2022}, month={5}, keywords={Few-shot learning Deep learning Meta-learning}, doi={10.1007/978-3-031-04409-0_23} }- Weizhi Huang
Ming He
Yongle Wang
Year: 2022
A Survey on Meta-learning Based Few-Shot Classification
MLICOM
Springer
DOI: 10.1007/978-3-031-04409-0_23
Abstract
Data-intensive applications have achieved great success in the field of machine learning. How to ensure that the machine can still learn correctly in the absence of labeled samples is the next challenging problem to be solved. This paper first introduces the problem definition of few-shot learning. Secondly, the existing small few-shot learning methods based on meta-learning are comprehensively summarized. Specifically, they are divided into three categories: metric-based learning methods, optimization-based learning methods and model-based learning methods. We conducted a series of comparisons among various methods in each category to show the advantages and disadvantages of each method. Finally, the limitations of existing methods are analyzed, and the future development direction of few-shot learning research is prospected.
