Few-shot Class-variable Incremental Audio Classification via Prototype Adaptation and Pseudo Class-variable Training
2026-06-08 • Artificial Intelligence
Artificial IntelligenceMachine Learning
AI summaryⓘ
The authors study a new problem where the number of sound classes in a recognition task can both increase and decrease over time, unlike previous work which only allowed increases. They propose a method that adapts class prototypes and uses special training to handle these changing classes. Their model has an encoder and a classifier that can change structure dynamically with the class number. Tests on three datasets show their method performs better than past approaches.
few-shot learningclass-incremental learningaudio classificationprototype adaptationdynamic classifierpseudo trainingclass-variable learningencoderclassifier
Authors
Yanxiong Li, Guoqing Chen, Qianqian Li, Sen Huang
Abstract
In the task of few-shot class-incremental audio classification, the number of classes is assumed to always increase without considering the possibility of decrease. However, the number of classes generally increases or decreases in practice. In this paper, we investigate a problem of Few-shot Class-variable Incremental Audio Classification (FCIAC), in which the number of classes increases or decreases. We propose a FCIAC method using prototype adaptation and pseudo class-variable training. The model in our method consists of an encoder and a classifier. The classifier is initialized by a class-variable prototype adaptation network, whose structure dynamically changes with the change of classes. In addition, we design a pseudo class-variable training strategy to enhance the model's adaptability to changing classes. Experiments on three public datasets show that our method exceeds previous methods in average accuracy. The code is at: https://github.com/cgq2971-afk/FCIAC.