Proceedings of the Korean Society of Broadcast Engineers Conference (한국방송∙미디어공학회:학술대회논문집)
- 2020.11a
- /
- Pages.244-247
- /
- 2020
Intra-Class Random Erasing (ICRE) augmentation for audio classification
- Kumar, Teerath (Kyung Hee University) ;
- Park, Jinbae (Kyung Hee University) ;
- Bae, Sung-Ho (Kyung Hee University)
- Published : 2020.11.28
Abstract
Data augmentation has been helpful in improving the performance in deep learning, when we have a limited data and random erasing is one of the augmentations that have shown impressive performance in deep learning in multiple domains. But the main issue is that sometime it loses good features when randomly selected region is erased by some random values, that does not improve performance as it should. We target that problem in way that good features should not be lost and also want random erasing at the same time. For that purpose, we introduce new augmentation technique named Intra-Class Random Erasing (ICRE) that focuses on data to learn robust features of the same class samples by randomly exchanging randomly selected region. We perform multiple experiments by using different models including resnet18, VGG16 over variety of the datasets including ESC10, UrbanSound8K. Our approach has shown effectiveness over others methods including random erasing.
Keywords