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...
| Hlavní autoři: | , , , , |
|---|---|
| Médium: | Článek |
| Jazyk: | English |
| Vydáno: |
MDPI AG
2021-03-01
|
| Edice: | Applied Sciences |
| Témata: | |
| On-line přístup: | https://www.mdpi.com/2076-3417/11/7/3043 |