# Prototypical Contrastive Learning For Improved Few-Shot Audio Classification

arXiv: https://arxiv.org/abs/2509.10074 · HTML: https://mlsanity.com/paper/2509.10074/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Builds on (most cited first, 16 of 16)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [TADAM: Task dependent adaptive metric for improved few-shot learning](https://mlsanity.com/paper/1805.10123/) (2018)
- [Deep Metric Learning with Angular Loss](https://mlsanity.com/paper/1708.01682/) (2017)
- [Meta-Curvature](https://mlsanity.com/paper/1902.03356/) (2019)
- [Few-Shot Classification with Contrastive Learning](https://mlsanity.com/paper/2209.08224/) (2022)
- [MetaAudio: A Few-Shot Audio Classification Benchmark](https://mlsanity.com/paper/2204.02121/) (2022)
- [Centroid-based deep metric learning for speaker recognition](https://mlsanity.com/paper/1902.02375/) (2019)
- [Spatial Contrastive Learning for Few-Shot Classification](https://mlsanity.com/paper/2012.13831/) (2020)
- [Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning](https://mlsanity.com/paper/2101.09499/) (2021)
- [Learning to match transient sound events using attentional similarity for few-shot sound recognition](https://mlsanity.com/paper/1812.01269/) (2018)
- [Training neural audio classifiers with few data](https://mlsanity.com/paper/1810.10274/) (2018)

## Built on by (most cited first, 2 of 2)

- [SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification](https://mlsanity.com/paper/2605.13672/) (2026)
- [Sample-Conditioned Representation Selection for Audio Few-Shot Learning](https://mlsanity.com/paper/2609.17076/) (2026)

## Abstract (arXiv)

Few-shot learning has emerged as a powerful paradigm for training models with limited labeled data, addressing challenges in scenarios where large-scale annotation is impractical. While extensive research has been conducted in the image domain, few-shot learning in audio classification remains relatively underexplored. In this work, we investigate the effect of integrating supervised contrastive loss into prototypical few shot training for audio classification. In detail, we demonstrate that angular loss further improves the performance compared to the standard contrastive loss. Our method leverages SpecAugment followed by a self-attention mechanism to encapsulate diverse information of augmented input versions into one unified embedding. We evaluate our approach on MetaAudio, a benchmark including five datasets with predefined splits, standardized preprocessing, and a comprehensive set of few-shot learning models for comparison. The proposed approach achieves state-of-the-art performance in a 5-way, 5-shot setting.