Episodic fine-tuning prototypical networks for optimization-based few-shot learning: Application to audio classification

TL;DR

This paper introduces a novel episodic fine-tuning approach for Prototypical Networks, enhancing few-shot audio classification performance by combining them with optimization-based algorithms like MAML and Meta-Curvature.

Contribution

It proposes a simple yet effective fine-tuning method for ProtoNet and integrates it with optimization-based FSL algorithms to improve adaptation in few-shot learning.

Findings

Significant performance improvements over standard ProtoNet on ESC-50 and Speech Commands v2 datasets.

The combined models outperform regular ProtoNet in few-shot audio classification.

The method is general and adaptable to other domains beyond audio.

Abstract

The Prototypical Network (ProtoNet) has emerged as a popular choice in Few-shot Learning (FSL) scenarios due to its remarkable performance and straightforward implementation. Building upon such success, we first propose a simple (yet novel) method to fine-tune a ProtoNet on the (labeled) support set of the test episode of a C-way-K-shot test episode (without using the query set which is only used for evaluation). We then propose an algorithmic framework that combines ProtoNet with optimization-based FSL algorithms (MAML and Meta-Curvature) to work with such a fine-tuning method. Since optimization-based algorithms endow the target learner model with the ability to fast adaption to only a few samples, we utilize ProtoNet as the target model to enhance its fine-tuning performance with the help of a specifically designed episodic fine-tuning strategy. The experimental results confirm that our proposed models, MAML-Proto and MC-Proto, combined with our unique fine-tuning method, outperform regular ProtoNet by a large margin in few-shot audio classification tasks on the ESC-50 and Speech Commands v2 datasets. We note that although we have only applied our model to the audio domain, it is a general method and can be easily extended to other domains.