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.

本文介绍了一种数据增强方法—— You Only Cut Once（YOCO），它将图像分为两个部分分别进行数据增强，可以提高样本数据的多样性和鼓励神经网络从局部信息中识别对象；该方法易于使用、不需要调参，并可以免费提升几乎所有增强项的性能。通过在 CIFAR 和 ImageNet 数据集上的实验证明，YOCO 可以无缝适应于不同的数据增强方法和神经网络架构，并带来了显著的性能提升，在某些情况下甚至超过了传统的图像级别增强方法。同时，该方法还可以为对比学习的预训练提供更强大的表示，并可在多个下游任务中更好地转移。最后，我们还研究了 YOCO 的多种变体，并分别分析了它们在不同设置下的性能表现。

一切只需一刀：单次切割增强数据