The Effects of Mixed Sample Data Augmentation are Class Dependent

Autor:	Lee, Haeil, Lee, Hansang, Kim, Junmo
Rok vydání:	2023
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	Mixed Sample Data Augmentation (MSDA) techniques, such as Mixup, CutMix, and PuzzleMix, have been widely acknowledged for enhancing performance in a variety of tasks. A previous study reported the class dependency of traditional data augmentation (DA), where certain classes benefit disproportionately compared to others. This paper reveals a class dependent effect of MSDA, where some classes experience improved performance while others experience degraded performance. This research addresses the issue of class dependency in MSDA and proposes an algorithm to mitigate it. The approach involves training on a mixture of MSDA and non-MSDA data, which not only mitigates the negative impact on the affected classes, but also improves overall accuracy. Furthermore, we provide in-depth analysis and discussion of why MSDA introduced class dependencies and which classes are most likely to have them. Comment: 21 pages, 18 figures, Overall Revision
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2307.09136 Zobrazit plný text záznamu View this record from Arxiv