[HTML][HTML] A survey on few-shot class-incremental learning

S Tian, L Li, W Li, H Ran, X Ning, P Tiwari - Neural Networks, 2024 - Elsevier
Large deep learning models are impressive, but they struggle when real-time data is not
available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for …

[HTML][HTML] Learning to detect an animal sound from five examples

I Nolasco, S Singh, V Morfi, V Lostanlen… - Ecological …, 2023 - Elsevier
Automatic detection and classification of animal sounds has many applications in
biodiversity monitoring and animal behavior. In the past twenty years, the volume of digitised …

A comprehensive review of few-shot action recognition

Y Wanyan, X Yang, W Dong, C Xu - ar**
sounds for solving a sequence of multi-label audio classification tasks. We design an …

[PDF][PDF] Active Few-Shot Learning for Sound Event Detection.

Y Wang, M Cartwright, JP Bello - Interspeech, 2022 - isca-archive.org
Few-shot learning has shown promising results in sound event detection where the model
can learn to recognize novel classes assuming a few labeled examples (typically five) are …

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

Y Li, W Cao, W **e, 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 …