Self-Supervised Transfer Learning from Natural Images for Sound Classification

We propose the implementation of transfer learning from natural images to audio-based images using self-supervised learning schemes. Through self-supervised learning, convolutional neural networks (CNNs) can learn the general representation of natural images without labels. In this study, a convolut...

ver descrição completa

Detalhes bibliográficos
Main Authors: Sungho Shin, Jongwon Kim, Yeonguk Yu, Seongju Lee, Kyoobin Lee
Formato: Artigo
Idioma:English
Publicado em: MDPI AG 2021-03-01
Colecção:Applied Sciences
Assuntos:
Acesso em linha:https://www.mdpi.com/2076-3417/11/7/3043