Learning Representations for New Sound Classes With Continual Self-Supervised Learning
In this paper, 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.
Code (1)
Tasks
Continual LearningContinual Self-Supervised LearningRepresentation LearningSelf-Supervised LearningSimilar Papers 제목 키워드 기반
Self-Supervised Training Enhances Online Continual Learning
In continual learning, a system must incrementally learn from a non-stationary data stream without catastrophic forgetting. Recently, multiple methods have been devised for incrementally learning classes on large-scale i…
Continual Learningimage-classificationImage ClassificationUCIL: An Unsupervised Class Incremental Learning Approach for Sound Event Detection
This work explores class-incremental learning (CIL) for sound event detection (SED), advancing adaptability towards real-world scenarios. CIL's success in domains like computer vision inspired our SED-tailored method, ad…
class-incremental learningClass Incremental LearningContinual LearningEvent Detection+3Self-Supervised Learning from Automatically Separated Sound Scenes
Real-world sound scenes consist of time-varying collections of sound sources, each generating characteristic sound events that are mixed together in audio recordings. The association of these constituent sound events wit…
Contrastive LearningSelf-Supervised LearningDiscriminative Sounding Objects Localization via Self-supervised Audiovisual Matching
Discriminatively localizing sounding objects in cocktail-party, i.e., mixed sound scenes, is commonplace for humans, but still challenging for machines. In this paper, we propose a two-stage learning framework to perform…
ObjectObject LocalizationUnsupervised Continual Learning and Self-Taught Associative Memory Hierarchies
We first pose the Unsupervised Continual Learning (UCL) problem: learning salient representations from a non-stationary stream of unlabeled data in which the number of object classes varies with time. Given limited label…
Continual LearningOnline Clustering