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...
Auteurs principaux: | Sungho Shin, Jongwon Kim, Yeonguk Yu, Seongju Lee, Kyoobin Lee |
---|---|
Format: | Article |
Langue: | English |
Publié: |
MDPI AG
2021-03-01
|
Collection: | Applied Sciences |
Sujets: | |
Accès en ligne: | https://www.mdpi.com/2076-3417/11/7/3043 |
Documents similaires
-
BattleSound: A Game Sound Benchmark for the Sound-Specific Feedback Generation in a Battle Game
par: Sungho Shin, et autres
Publié: (2023-01-01) -
Semi-Supervised NMF-CNN for Sound Event Detection
par: Teck Kai Chan, et autres
Publié: (2021-01-01) -
Weakly Supervised U-Net with Limited Upsampling for Sound Event Detection
par: Sangwon Lee, et autres
Publié: (2023-06-01) -
Transfer learning application of self-supervised learning in ARPES
par: Sandy Adhitia Ekahana, et autres
Publié: (2023-01-01) -
From Self-supervised Learning to Transfer Learning with Musculoskeletal Radiographs
par: Hinterwimmer Florian, et autres
Publié: (2022-09-01)