paper-with-me

Papers

Learning Representations for New Sound Classes With Continual Self-Supervised Learning

2022-05-15 · Zhepei Wang, Cem Subakan, Xilin Jiang, Junkai Wu, Efthymios Tzinis, Mirco Ravanelli, Paris Smaragdis

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.

📄 PDF Abstract BibTeX arXiv:2205.07390

Code (1)

zhepeiw/cssl_sound 공식 구현 pytorch

Tasks

Continual LearningContinual Self-Supervised LearningRepresentation LearningSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Self-Supervised Training Enhances Online Continual Learning

2021-03-25 · Jhair Gallardo, Tyler L. Hayes, Christopher Kanan

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 Classification

UCIL: An Unsupervised Class Incremental Learning Approach for Sound Event Detection

2024-07-04 · Yang Xiao, Rohan Kumar Das

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+3

Self-Supervised Learning from Automatically Separated Sound Scenes

2021-05-05 · Eduardo Fonseca, Aren Jansen, Daniel P. W. Ellis, Scott Wisdom 외

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 Learning

Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching

2020-10-12 · NeurIPS 2020 12 · Di Hu, Rui Qian, Minyue Jiang, Xiao Tan 외

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 Localization

Unsupervised Continual Learning and Self-Taught Associative Memory Hierarchies

2019-03-24 · ICLR Workshop LLD 2019 · James Smith, Seth Baer, Zsolt Kira, Constantine Dovrolis

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