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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Si, Yongjie, Li, Yanxiong, Tan, Jiaxin, He, Qianhua, Kwak, Il-Youp
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916806471450624
author Si, Yongjie
Li, Yanxiong
Tan, Jiaxin
He, Qianhua
Kwak, Il-Youp
author_facet Si, Yongjie
Li, Yanxiong
Tan, Jiaxin
He, Qianhua
Kwak, Il-Youp
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18406
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fully Few-shot Class-incremental Audio Classification Using Multi-level Embedding Extractor and Ridge Regression Classifier
Si, Yongjie
Li, Yanxiong
Tan, Jiaxin
He, Qianhua
Kwak, Il-Youp
Audio and Speech Processing
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.
title Fully Few-shot Class-incremental Audio Classification Using Multi-level Embedding Extractor and Ridge Regression Classifier
topic Audio and Speech Processing
url https://arxiv.org/abs/2506.18406