BROWSE
Detail
Journal Article
Online Continual Learning in Acoustic Scene Classification: An Empirical Study
- Authors
- Donghee Ha, Mooseop Kim, Chi Yoon Jeong
- Issue Date
- 2023-08
- Citation
- Sensors, v.23, no.15, pp.1-19
- ISSN
- 1424-8220
- Publisher
- Multidisciplinary Digital Publishing Institute (MDPI)
- Language
- English
- Type
- Journal Article
- Abstract
- Numerous deep learning methods for acoustic scene classification (ASC) have been proposed to improve the classification accuracy of sound events. However, only a few studies have focused on continual learning (CL) wherein a model continually learns to solve issues with task changes. Therefore, in this study, we systematically analyzed the performance of ten recent CL methods to provide guidelines regarding their performances. The CL methods included two regularization-based methods and eight replay-based methods. First, we defined realistic and difficult scenarios such as online class-incremental (OCI) and online domain-incremental (ODI) cases for three public sound datasets. Then, we systematically analyzed the performance of each CL method in terms of average accuracy, average forgetting, and training time. In OCI scenarios, iCaRL and SCR showed the best performance for small buffer sizes, and GDumb showed the best performance for large buffer sizes. In ODI scenarios, SCR adopting supervised contrastive learning consistently outperformed the other methods, regardless of the memory buffer size. Most replay-based methods have an almost constant training time, regardless of the memory buffer size, and their performance increases with an increase in the memory buffer size. Based on these results, we must first consider GDumb/SCR for the continual learning methods for ASC.
- KSP Keywords
- Acoustic Scene Classification, Best performance, Buffer Size, Empirical study, Learning methods, Small buffer, Training time, classification accuracy, deep learning(DL), sound events
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
(CC BY)
