# Few-shot Class-incremental Audio Classification Using Adaptively-refined Prototypes

arXiv: https://arxiv.org/abs/2305.18045 · HTML: https://mlsanity.com/paper/2305.18045/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2023.

## Built on by (most cited first, 6 of 6)

- [Towards Robust Few-shot Class Incremental Learning in Audio Classification using Contrastive Representation](https://mlsanity.com/paper/2407.19265/) (2024)
- [Meta-Learning in Audio and Speech Processing: An End to End Comprehensive Review](https://mlsanity.com/paper/2408.10330/) (2024)
- [Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypes](https://mlsanity.com/paper/2607.01297/) (2026)
- [When Sensing Varies with Contexts: Context Probing for Tactile Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2603.25115/) (2026)
- [Few-shot Class-variable Incremental Audio Classification via Prototype Adaptation and Pseudo Class-variable Training](https://mlsanity.com/paper/2606.08898/) (2026)
- [SPECTRA: Subspace-Preserving Embedding Calibration, Transport, and Replay for Fully Few-Shot Class-Incremental Audio Classification](https://mlsanity.com/paper/2608.25054/) (2026)

## Abstract (arXiv)

New classes of sounds constantly emerge with a few samples, making it challenging for models to adapt to dynamic acoustic environments. This challenge motivates us to address the new problem of few-shot class-incremental audio classification. This study aims to enable a model to continuously recognize new classes of sounds with a few training samples of new classes while remembering the learned ones. To this end, we propose a method to generate discriminative prototypes and use them to expand the model's classifier for recognizing sounds of new and learned classes. The model is first trained with a random episodic training strategy, and then its backbone is used to generate the prototypes. A dynamic relation projection module refines the prototypes to enhance their discriminability. Results on two datasets (derived from the corpora of Nsynth and FSD-MIX-CLIPS) show that the proposed method exceeds three state-of-the-art methods in average accuracy and performance dropping rate.