Few-shot class-incremental audio classification using dynamically expanded classifier with self-attention modified prototypes

Y Li, W Cao, W Xie, J Li… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
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 …
被引用次数：6 相关文章

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

Y Li, W Cao, W Xie, J Li, E Benetos - arXiv preprint arXiv:2305.19539, 2023 - arxiv.org
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 …

Few-Shot Class-Incremental Audio Classification Using Dynamically Expanded Classifier With Self-Attention Modified Prototypes

Y Li, W Cao, W Xie, J Li, E Benetos - IEEE Transactions on Multimedia, 2024 - dl.acm.org
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 …

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

Y Li, W Cao, W Xie, J Li, E Benetos - arXiv e-prints, 2023 - ui.adsabs.harvard.edu
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 …
[PDF] qmul.ac.uk

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

Y Li, W Cao, W Xie, J Li, E Benetos - IEEE Transactions on …, 2023 - qmro.qmul.ac.uk
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 …