.png){kind=icon}
返回
Learning Representations for New Sound Classes With Continual Self-Supervised Learning
.png){kind=icon}
OA
AI
DOI：10.1109/LSP.2022.3229643.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this article, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without relying on labeled data. For this purpose, we propose adopting representation learning, where an encoder is trained using unlabeled data. This learning framework enables the study and implementation of a practically relevant use case where only a small amount of the labels is available in a continual learning context. We also make the empirical observation that a similarity-based representation learning method within this framework is robust to forgetting even if no explicit mechanism against forgetting is employed. We show that this approach obtains similar performance compared to several distillation-based continual learning methods when employed on self-supervised representation learning methods.
Keyword:
Continual learning
representation learning
self-supervised learning
sound classification
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
.png){kind=icon}
The effect of maternal exercise on umbilical artery blood flow in pregnancy-induced hypertension
PREAI
分享收藏分享收藏
Fiber Reinforced Polymer Confinement of Bridge Columns Suffering from Premature Bars’ Buckling – Strength empirical model纤维增强聚合物约束受早期钢筋屈曲影响的桥梁墩柱——强度经验模型
PREAI
分享收藏
查看更多内容