Self-Supervised Transfer Learning from Natural Images for Sound Classification

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...

Cijeli opis

Bibliografski detalji
Glavni autori: Sungho Shin, Jongwon Kim, Yeonguk Yu, Seongju Lee, Kyoobin Lee
Format: Članak
Jezik:English
Izdano: MDPI AG 2021-03-01
Serija:Applied Sciences
Teme:
deep learning
sound event detection
self-supervised learning
transfer learning
natural image
Online pristup:https://www.mdpi.com/2076-3417/11/7/3043

Internet

https://www.mdpi.com/2076-3417/11/7/3043

Slični predmeti