Problem
Research questions and friction points this paper is trying to address.
few-shot
class-variable
incremental learning
audio classification
class-incremental
Few-shot Class-variable Incremental Audio Classification via Prototype Adaptation and Pseudo Class-variable Training
🤖 AI Summary
This work addresses the challenge of audio classification under few-shot settings where the number of classes dynamically increases or decreases over time. It introduces, for the first time, the task of class-variable incremental audio classification, extending beyond conventional incremental learning that only accommodates new classes. To tackle this problem, the authors propose a prototype-adaptive network with a dynamic architecture and a pseudo class-variable training strategy that simulates scenarios involving both the addition and removal of classes, thereby enhancing the model’s adaptability to class fluctuations. Extensive experiments on three public datasets demonstrate that the proposed method achieves significantly higher average accuracy compared to existing approaches, confirming its effectiveness and robustness in handling dynamic class sets under data-scarce conditions.
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
few-shot learning
class-incremental learning
prototype adaptation
pseudo training
audio classification
🔎 Similar Papers
No similar papers found.
