Year: 2022
Type: preprint
Abstract: Mixup is a data augmentation method that generates new data points by mixing a pair of input data. While mixup generally improves the prediction performance, it sometimes degrades the performance. In this paper, we first identify the main causes of this phenomenon by theoretically and empirically analyzing the mixup algorithm. To resolve this, we propose GenLabel, a simple yet effective relabeling algorithm designed for mixup. In particular, GenLabel helps the mixup algorithm correctly label mixup samples by learning the class-conditional data distribution using generative models. Via extensive theoretical and empirical analysis, we show that mixup, when used together with GenLabel, can effectively resolve the aforementioned phenomenon, improving the generalization performance and the adversarial robustness.
Source: arXiv (Cornell University)
Authors: Sohn, Jy-yong, Shang, Liang, Chen, Hongxu, Moon, Jaekyun, Papailiopoulos, Dimitris, Lee, Kangwook
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: University of Wisconsin-Madison
OpenAlex ID: W4221149927