Learning from Few Examples: A Summary of Approaches to Few-Shot Learning

TL;DR

This paper surveys recent few-shot learning algorithms, emphasizing methods that enable models to learn effectively from limited data, reducing data collection costs and computational resources.

Contribution

It provides a comprehensive overview of recent approaches to few-shot learning, categorizing them into meta-learning, transfer learning, and hybrid methods.

Findings

Meta-learning approaches adapt quickly to new tasks.

Transfer learning leverages pre-trained models for few-shot scenarios.

Hybrid methods combine multiple techniques for improved performance.

Abstract

Few-Shot Learning refers to the problem of learning the underlying pattern in the data just from a few training samples. Requiring a large number of data samples, many deep learning solutions suffer from data hunger and extensively high computation time and resources. Furthermore, data is often not available due to not only the nature of the problem or privacy concerns but also the cost of data preparation. Data collection, preprocessing, and labeling are strenuous human tasks. Therefore, few-shot learning that could drastically reduce the turnaround time of building machine learning applications emerges as a low-cost solution. This survey paper comprises a representative list of recently proposed few-shot learning algorithms. Given the learning dynamics and characteristics, the approaches to few-shot learning problems are discussed in the perspectives of meta-learning, transfer learning, and hybrid approaches (i.e., different variations of the few-shot learning problem).