# Few-shot Class-incremental Audio Classification Using Stochastic Classifier

arXiv: https://arxiv.org/abs/2306.02053 · HTML: https://mlsanity.com/paper/2306.02053/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2023.

## Built on by (most cited first, 4 of 4)

- [Class-incremental Learning for Time Series: Benchmark and Evaluation](https://mlsanity.com/paper/2402.12035/) (2024)
- [Towards Robust Few-shot Class Incremental Learning in Audio Classification using Contrastive Representation](https://mlsanity.com/paper/2407.19265/) (2024)
- [Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypes](https://mlsanity.com/paper/2607.01297/) (2026)
- [Few-shot Class-variable Incremental Audio Classification via Prototype Adaptation and Pseudo Class-variable Training](https://mlsanity.com/paper/2606.08898/) (2026)

## Abstract (arXiv)

It is generally assumed that number of classes is fixed in current audio classification methods, and the model can recognize pregiven classes only. When new classes emerge, the model needs to be retrained with adequate samples of all classes. If new classes continually emerge, these methods will not work well and even infeasible. In this study, we propose a method for fewshot class-incremental audio classification, which continually recognizes new classes and remember old ones. The proposed model consists of an embedding extractor and a stochastic classifier. The former is trained in base session and frozen in incremental sessions, while the latter is incrementally expanded in all sessions. Two datasets (NS-100 and LS-100) are built by choosing samples from audio corpora of NSynth and LibriSpeech, respectively. Results show that our method exceeds four baseline ones in average accuracy and performance dropping rate. Code is at https://github.com/vinceasvp/meta-sc.