Meta-learning Approaches for Few-Shot Learning: A Survey of Recent Advances

Despite its astounding success in learning deeper multi-dimensional data, the performance of deep learning declines on new unseen tasks mainly due to its focus on same-distribution prediction. Moreover, deep learning is notorious for poor generalization from few samples. Meta-learning is a promising...

Full description

Saved in:
Bibliographic Details
Published in:ACM computing surveys 2024-12, Vol.56 (12), p.1-41, Article 294
Main Authors: Gharoun, Hassan, Momenifar, Fereshteh, Chen, Fang, Gandomi, Amir
Format: Article
Language:English
Subjects:
Computing methodologies
Deep learning
Image representations
Learning paradigms
Multidimensional data
Neural networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Despite its astounding success in learning deeper multi-dimensional data, the performance of deep learning declines on new unseen tasks mainly due to its focus on same-distribution prediction. Moreover, deep learning is notorious for poor generalization from few samples. Meta-learning is a promising approach that addresses these issues by adapting to new tasks with few-shot datasets. This survey first briefly introduces meta-learning and then investigates state-of-the-art meta-learning methods and recent advances in: (i) metric-based, (ii) memory-based, (iii), and learning-based methods. Finally, current challenges and insights for future researches are discussed.
ISSN:0360-0300
1557-7341
DOI:10.1145/3659943