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...
Những tác giả chính: | Sungho Shin, Jongwon Kim, Yeonguk Yu, Seongju Lee, Kyoobin Lee |
---|---|
Định dạng: | Bài viết |
Ngôn ngữ: | English |
Được phát hành: |
MDPI AG
2021-03-01
|
Loạt: | Applied Sciences |
Những chủ đề: | |
Truy cập trực tuyến: | https://www.mdpi.com/2076-3417/11/7/3043 |
Những quyển sách tương tự
-
BattleSound: A Game Sound Benchmark for the Sound-Specific Feedback Generation in a Battle Game
Bằng: Sungho Shin, et al.
Được phát hành: (2023-01-01) -
Semi-Supervised NMF-CNN for Sound Event Detection
Bằng: Teck Kai Chan, et al.
Được phát hành: (2021-01-01) -
Weakly Supervised U-Net with Limited Upsampling for Sound Event Detection
Bằng: Sangwon Lee, et al.
Được phát hành: (2023-06-01) -
Transfer learning application of self-supervised learning in ARPES
Bằng: Sandy Adhitia Ekahana, et al.
Được phát hành: (2023-01-01) -
From Self-supervised Learning to Transfer Learning with Musculoskeletal Radiographs
Bằng: Hinterwimmer Florian, et al.
Được phát hành: (2022-09-01)