Back to Search Start Over

You Only Cut Once: Boosting Data Augmentation with a Single Cut

Authors :
Han, Junlin
Fang, Pengfei
Li, Weihao
Hong, Jie
Armin, Mohammad Ali
Reid, Ian
Petersson, Lars
Li, Hongdong
Publication Year :
2022

Abstract

We present You Only Cut Once (YOCO) for performing data augmentations. YOCO cuts one image into two pieces and performs data augmentations individually within each piece. Applying YOCO improves the diversity of the augmentation per sample and encourages neural networks to recognize objects from partial information. YOCO enjoys the properties of parameter-free, easy usage, and boosting almost all augmentations for free. Thorough experiments are conducted to evaluate its effectiveness. We first demonstrate that YOCO can be seamlessly applied to varying data augmentations, neural network architectures, and brings performance gains on CIFAR and ImageNet classification tasks, sometimes surpassing conventional image-level augmentation by large margins. Moreover, we show YOCO benefits contrastive pre-training toward a more powerful representation that can be better transferred to multiple downstream tasks. Finally, we study a number of variants of YOCO and empirically analyze the performance for respective settings. Code is available at GitHub.<br />Comment: ICML 2022, Code: https://github.com/JunlinHan/YOCO

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2201.12078
Document Type :
Working Paper