Differentiable Style Searching: An Online Automatic Data Augmentation Method

被引：0

作者：

Luo Y. ^{[1
]}

Yu J. ^{[2
]}

机构：

[1] School of Software Technology, Zhejiang University, Ningbo

[2] School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan

来源：

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | 2023年 / 35卷 / 04期

关键词：

automatic data augmentation; deep learning; model generalization; style transfer;

D O I：

10.3724/SP.J.1089.2023.19348

中图分类号：

学科分类号：

摘要：

Aiming at the problems of offline image transformation and limited search space in existing data enhancement methods, an online automatic data enhancement (ODA) method is proposed. The core of ODA is a micro-style search module, which can perceive the current data enhancement required by the task model by directly transmitting training losses, and generate more difficult stylized pictures online to expand the training set by means of anti-search, so as to effectively help the model complete the generalization on a variety of unknown styles. On the cross-domain image classification task of MNIST, MNIST-M, SVHN and USPS data sets, as well as the cross-domain scene semantic segmentation task of Cityscapes and GTA5 data sets, compared with other five typical data enhancement methods, ODA method can improve classification accuracy by at least 2% under Acc metric and 3% to 7% under mIoU metric of semantic segmentation task, which proves that ODA extends the search space of traditional automatic data enhancement methods in the direction of image style and enhances the generalization ability of network. © 2023 Institute of Computing Technology. All rights reserved.

引用

页码：553 / 561

页数：8

共 50 条

[1] Cordts M, Omran M, Ramos S, Et al., The cityscapes dataset for semantic urban scene understanding, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213-3223, (2016)
[2] Van Dyk D A, Meng X L., The art of data augmentation, Journal of Computational and Graphical Statistics, 10, 1, pp. 1-50, (2001)
[3] Hobert J P., The data augmentation algorithm: theory and methodology, Handbook of Markov Chain Monte Carlo, pp. 253-293, (2011)
[4] Shorten C, Khoshgoftaar T M., A survey on image data augmentation for deep learning, Journal of Big Data, 6, 1, pp. 1-48, (2019)
[5] Zhong Z, Zheng L, Kang G L, Et al., Random erasing data augmentation, Proceedings of the AAAI Conference on Artificial Intelligence, pp. 13001-13008, (2020)
[6] Zoph B, Cubuk E D, Ghiasi G, Et al., Learning data augmentation strategies for object detection, Proceedings of the European Conference on Computer Vision, pp. 566-583, (2020)
[7] Cubuk E D, Zoph B, Mane D, Et al., AutoAugment: learning augmentation strategies from data, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 113-123, (2019)
[8] Hataya R, Zdenek J, Yoshizoe K, Et al., Faster autoaugment: learning augmentation strategies using backpropagation, Proceedings of the European Conference on Computer Vision, pp. 1-16, (2020)
[9] Li H, Zhang X P, Tian Q, Et al., Attribute mix: semantic data augmentation for fine grained recognition, Proceedings of the IEEE International Conference on Visual Communications and Image Processing, pp. 243-246, (2020)
[10] Zhao A, Balakrishnan G, Durand F, Et al., Data augmentation using learned transformations for one-shot medical image segmentation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8535-8545, (2019)

← 1 2 3 4 5 →