Meta-learning approaches for few-shot learning: A survey of recent advances

TL;DR

This survey reviews recent meta-learning methods that enable deep models to adapt quickly to new tasks with limited data, addressing generalization and few-shot learning challenges.

Contribution

It provides a comprehensive overview of recent advances in meta-learning techniques, categorizing methods into metric-based, memory-based, and learning-based approaches.

Findings

Meta-learning improves few-shot learning performance.

Recent methods show significant progress in rapid adaptation.

Challenges remain in scalability and robustness.

Abstract

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.