most citedFew-shot Class-incremental Audio Classification Using Dynamically Expanded Classifier with Self-attention Modified Prototypes

23 citations · 23 across the 1 of their papers we have counts for

collaborators
Showing eess.ASShow all

1 paper · 1 filter

eess.AS2023★ 23 cited

Few-shot Class-incremental Audio Classification Using Dynamically Expanded Classifier with Self-attention Modified Prototypes

Yanxiong Li, Wenchang Cao, Wei Xie +2

Most existing methods for audio classification assume that the vocabulary of audio classes to be classified is fixed. When novel (unseen) audio classes appear, audio classification…