EPISODIC FINE-TUNING PROTOTYPICAL NETWORKS FOR OPTIMIZATION-BASED FEW-SHOT LEARNING: APPLICATION TO AUDIO CLASSIFICATION - Archive ouverte HAL
Conference Papers Year : 2024

EPISODIC FINE-TUNING PROTOTYPICAL NETWORKS FOR OPTIMIZATION-BASED FEW-SHOT LEARNING: APPLICATION TO AUDIO CLASSIFICATION

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.
Fichier principal
Vignette du fichier
Proto-MAML_MLSP_2024.pdf (519.78 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04720291 , version 1 (03-10-2024)

Identifiers

  • HAL Id : hal-04720291 , version 1

Cite

Xuanyu Zhuang, Geoffroy Peeters, Gaël Richard. EPISODIC FINE-TUNING PROTOTYPICAL NETWORKS FOR OPTIMIZATION-BASED FEW-SHOT LEARNING: APPLICATION TO AUDIO CLASSIFICATION. 2024 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2024), Sep 2024, London (UK), United Kingdom. ⟨hal-04720291⟩
69 View
21 Download

Share

More