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...
主要な著者: | Sungho Shin, Jongwon Kim, Yeonguk Yu, Seongju Lee, Kyoobin Lee |
---|---|
フォーマット: | 論文 |
言語: | English |
出版事項: |
MDPI AG
2021-03-01
|
シリーズ: | Applied Sciences |
主題: | |
オンライン・アクセス: | https://www.mdpi.com/2076-3417/11/7/3043 |
類似資料
-
BattleSound: A Game Sound Benchmark for the Sound-Specific Feedback Generation in a Battle Game
著者:: Sungho Shin, 等
出版事項: (2023-01-01) -
Semi-Supervised NMF-CNN for Sound Event Detection
著者:: Teck Kai Chan, 等
出版事項: (2021-01-01) -
Weakly Supervised U-Net with Limited Upsampling for Sound Event Detection
著者:: Sangwon Lee, 等
出版事項: (2023-06-01) -
Transfer learning application of self-supervised learning in ARPES
著者:: Sandy Adhitia Ekahana, 等
出版事項: (2023-01-01) -
From Self-supervised Learning to Transfer Learning with Musculoskeletal Radiographs
著者:: Hinterwimmer Florian, 等
出版事項: (2022-09-01)