Sample-customized implicit semantic data augmentation for neural networks regularization

Open Webpage

Xu Kang, Jia Jia, Bing Zhang, Xinzhi Li

Published: 2025, Last Modified: 04 Nov 2025Neurocomputing 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•A novel sample-level semantic data augmentation method is proposed.•The method conducts sample-customized data augmentation in deep feature space.•Experiments on public datasets verified the method is effective and efficient.