Data Augmentation Using Random Image Cropping and Patching for Deep CNNs

• Published in: IEEE transactions on circuits and systems for video technology Vol. 30; no. 9; pp. 2917 - 2931
• Main Authors: Takahashi, Ryo, Matsubara, Takashi, Uehara, Kuniaki
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Computer vision; convolutional neural network; Convolutional neural networks; Data augmentation; Image classification; Image color analysis; Image processing; image-caption retrieval; Jitter; Labels; Patching; Principal component analysis; Regularization; Task analysis; Training
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2019.2935128

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 of the soft labels. 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, an image-caption retrieval task using Microsoft COCO, and other computer vision tasks.