Loading...
Please wait, while we are loading the content...
Similar Documents
Self-Supervised Transfer Learning from Natural Images for Sound Classification
| Content Provider | MDPI |
|---|---|
| Author | Shin, Sungho Kim, Jongwon Yu, Yeonguk Lee, Seongju Lee, Kyoobin |
| Copyright Year | 2021 |
| Description | 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 convolutional neural network was pre-trained with natural images (ImageNet) via self-supervised learning; subsequently, it was fine-tuned on the target audio samples. Pre-training with the self-supervised learning scheme significantly improved the sound classification performance when validated on the following benchmarks: ESC-50, UrbanSound8k, and GTZAN. The network pre-trained via self-supervised learning achieved a similar level of accuracy as those pre-trained using a supervised method that require labels. Therefore, we demonstrated that transfer learning from natural images contributes to improvements in audio-related tasks, and self-supervised learning with natural images is adequate for pre-training scheme in terms of simplicity and effectiveness. |
| Starting Page | 3043 |
| e-ISSN | 20763417 |
| DOI | 10.3390/app11073043 |
| Journal | Applied Sciences |
| Issue Number | 7 |
| Volume Number | 11 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2021-03-29 |
| Access Restriction | Open |
| Subject Keyword | Applied Sciences Artificial Intelligence Deep Learning Sound Event Detection Self-supervised Learning Transfer Learning Natural Image |
| Content Type | Text |
| Resource Type | Article |
