Fully Few-shot Class-incremental Audio Classification Using Multi-level Embedding Extractor and Ridge Regression Classifier

2025/06/23 by Si, Yongjie, Li, Yanxiong, Tan, Jiaxin +2
#Audio and Speech Processing (eess.AS) #FOS: Electrical engineering #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2506.18406

Abstract

In the task of Few-shot Class-incremental Audio Classification (FCAC), training samples of each base class are required to be abundant to train model. However, it is not easy to collect abundant training samples for many base classes due to data scarcity and high collection cost. We discuss a more realistic issue, Fully FCAC (FFCAC), in which training samples of both base and incremental classes are only a few. Furthermore, we propose a FFCAC method using a model which is decoupled into a multi-level embedding extractor and a ridge regression classifier. The embedding extractor consists of an encoder of audio spectrogram Transformer and a fusion module, and is trained in the base session but frozen in all incremental sessions. The classifier is updated continually in each incremental session. Results on three public datasets show that our method exceeds current methods in accuracy, and has advantage over most of them in complexity. The code is at https://github.com/YongjieSi/MAR.

Citations

• Low-Complexity Acoustic Scene Classification Using Parallel Attention-Convolution Network
• Fully Few-shot Class-incremental Audio Classification Using Expandable Dual-embedding Extractor
• On the Transferability of Large-Scale Self-Supervision to Few-Shot Audio Classification
• Continual Learning with Pre-Trained Models: A Survey
• Class-Incremental Learning for Multi-Label Audio Classification
• On the choice of the optimal temporal support for audio classification with Pre-trained embeddings
• Lightweight Speaker Verification Using Transformation Module with Feature Partition and Fusion
• Zero- and Few-shot Sound Event Localization and Detection
• Class-Incremental Grouping Network for Continual Audio-Visual Learning
• Few-shot Class-incremental Audio Classification Using Stochastic Classifier
• Few-shot Class-incremental Audio Classification Using Adaptively-refined Prototypes
• Learning from Taxonomy: Multi-label Few-Shot Classification for Everyday Sound Recognition
• Speaker verification using attentive multi-scale convolutional recurrent network
• Forward Compatible Few-Shot Class-Incremental Learning
• Domestic activities clustering from audio recordings using convolutional capsule autoencoder network
• Few-Shot Incremental Learning with Continually Evolved Classifiers
• AST: Audio Spectrogram Transformer
• Acoustic Scene Clustering Using Joint Optimization of Deep Embedding Learning and Clustering Iteration
• Sound Event Detection with Depthwise Separable and Dilated Convolutions
• Sound event detection via dilated convolutional recurrent neural networks
• Learning without Memorizing
• Attention Is All You Need
• iCaRL: Incremental Classifier and Representation Learning
• Ridge Regression: Biased Estimation for Nonorthogonal Problems

Related

• Fully Few-shot Class-incremental Audio Classification Using Expandable Dual-embedding Extractor
• Few-shot Class-incremental Audio Classification Using Stochastic Classifier
• Towards Robust Few-shot Class Incremental Learning in Audio Classification using Contrastive Representation
• Few-shot Class-incremental Audio Classification Using Adaptively-refined Prototypes
• AudioCIL: A Python Toolbox for Audio Class-Incremental Learning with Multiple Scenes