Data Augmentation using Random Image Cropping and Patching for Deep CNNs
This addresses overfitting in deep learning for image tasks, offering an incremental improvement over existing augmentation methods.
The authors tackled overfitting in deep CNNs by proposing RICAP, a data augmentation technique that randomly crops and patches four images with mixed labels, achieving a new state-of-the-art test error of 2.19% on CIFAR-10 and improved results on other datasets.
Deep convolutional neural networks (CNNs) have achieved remarkable results in image processing tasks. However, their high expression ability risks overfitting. Consequently, data augmentation techniques have been proposed to prevent overfitting while enriching datasets. Recent CNN architectures with more parameters are rendering traditional data augmentation techniques insufficient. In this study, we propose a new data augmentation technique called random image cropping and patching (RICAP) which randomly crops four images and patches them to create a new training image. Moreover, RICAP mixes the class labels of the four images, resulting in an advantage similar to label smoothing. We evaluated RICAP with current state-of-the-art CNNs (e.g., the shake-shake regularization model) by comparison with competitive data augmentation techniques such as cutout and mixup. RICAP achieves a new state-of-the-art test error of $2.19\%$ on CIFAR-10. We also confirmed that deep CNNs with RICAP achieve better results on classification tasks using CIFAR-100 and ImageNet and an image-caption retrieval task using Microsoft COCO.