Grid cut and mix: flexible and efficient data augmentation

Shuai Feng; Shengtong Yang; Zhaodong Niu; Jianbin Xie; Mingshan Wei; Peiqin Li

doi:10.1117/12.2589385

27 January 2021 Grid cut and mix: flexible and efficient data augmentation

Shuai Feng, Shengtong Yang, Zhaodong Niu, Jianbin Xie, Mingshan Wei, Peiqin Li

Proceedings Volume 11720, Twelfth International Conference on Graphics and Image Processing (ICGIP 2020); 1172028 (2021) https://doi.org/10.1117/12.2589385
Event: Twelfth International Conference on Graphics and Image Processing, 2020, Xi'an, China

Abstract

Data augmentation plays an indispensable role in expanding datasets and preventing neural network overfitting. In this paper, we analyzed the advantages and disadvantages of information dropping and information mixing methods in data augmentation. Then we combine the advantage of information dropping and information mixing, and propose Gridcut and Gridmix. Gridcut is based on the structured deletion of the input images like Gridmask. The size and shape of the deleted areas can be flexibly adjusted according to the Characteristics of the dataset. Based on this Gridcut, Gridmix interpolates pixel information of other images on the deleted areas. Comparative experiments demonstrate that our methods outperform the state-of-the-art augmentation strategies on CIFAR classification tasks. By adjusting the parameters, our method can also be flexibly expanded into Cutout, Cutmix and Gridmask.

Citation Download Citation

Shuai Feng, Shengtong Yang, Zhaodong Niu, Jianbin Xie, Mingshan Wei, and Peiqin Li "Grid cut and mix: flexible and efficient data augmentation", Proc. SPIE 11720, Twelfth International Conference on Graphics and Image Processing (ICGIP 2020), 1172028 (27 January 2021); https://doi.org/10.1117/12.2589385

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available