Skip to yearly menu bar Skip to main content


Spotlight

GenLabel: Mixup Relabeling using Generative Models

Jy yong Sohn · Liang Shang · Hongxu Chen · Jaekyun Moon · Dimitris Papailiopoulos · Kangwook Lee

Ballroom 3 & 4

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 theoretical and empirical analysis, we show that mixup, when used together with GenLabel, can effectively resolve the aforementioned phenomenon, improving the accuracy of mixup-trained model.

Chat is not available.