Data augmentation method for insulators based on Cycle GAN

被引：4

作者：

Ye R. ^{[1
,3
]}

Boukerche A. ^{[2
]}

Yu X.-S. ^{[1
]}

Zhang C. ^{[3
]}

Yan B. ^{[1
,3
]}

Zhou X.-J. ^{[1
,3
]}

机构：

[1] School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu

[2] School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa

[3] Yangtze River Delta Research Institute (Huzhou), University of Electronic Science and Technology of China, Huzhou

来源：

Journal of Electronic Science and Technology | 2024年 / 22卷 / 02期

基金：

中国国家自然科学基金;

关键词：

Data expansion; Deep learning; Generate confrontation network; Insulator;

D O I：

10.1016/j.jnlest.2024.100250

中图分类号：

学科分类号：

摘要：

Data augmentation is an important task of using existing data to expand data sets. Using generative countermeasure network technology to realize data augmentation has the advantages of high-quality generated samples, simple training, and fewer restrictions on the number of generated samples. However, in the field of transmission line insulator images, the freely synthesized samples are prone to produce fuzzy backgrounds and disordered samples of the main insulator features. To solve the above problems, this paper uses cycle generative adversarial network (Cycle-GAN) used for domain conversion in the generation countermeasure network as the initial framework and uses the self-attention mechanism and the channel attention mechanism to assist the conversion to realize the mutual conversion of different insulator samples. The attention module with prior knowledge is used to build the generation countermeasure network, and the GAN model with local controllable generation is built to realize the directional generation of insulator belt defect samples. The experimental results show that the samples obtained by this method are improved in a number of quality indicators, and the quality effect of the samples obtained is excellent, which has a reference value for the data expansion of insulator images. © 2024 The Authors

引用

共 19 条

[1]

Tokozume Y., Ushiku Y., Harada T., Learning from between- class examples for deep sound recognition, Proc. of the 6th Intl. Conf. on Learning Representations, Vancouver, Canada, pp. 1-13, (2018)

[2]

Takahashi R., Matsubara T., Uehara Ricap K., Random image cropping and patching data augmentation for deep CNNs, Proc. Of the 10th Asian Conf. on Machine Learning, Beijing, China, pp. 786-798, (2018)

[3]

Goodfellow I.J., Pouget-Abadie J., Mirza M., Et al., Generative adversarial nets, Proc. of the 27th Intl. Conf. on Neural Information Processing Systems, Montreal, Canada, pp. 2672-2680, (2014)

[4]

Antoniou A., Storkey A., Edwards H., Data Augmentation Generative Adversarial Networks

[5]

Lake B.M., Salakhutdinov R., Tenenbaum J.B., Human-level concept learning through probabilistic program induction, Science, 350, 6266, pp. 1332-1338, (2015)

[6]

Radford A., Metz L., Chintala S., Unsupervised representation learning with deep convolutional generative adversarial networks, Proc. Of the 4th Intl. Conf. on Learning Representations, San Juan, America, pp. 1-15, (2016)

[7]

Frid-Adar M., Klang E., Amitai M., Goldberger J., Greenspan H., Synthetic data augmentation using GAN for improved liver lesion classification, Proc. Of the 15th IEEE Intl. Symp. on Biomedical Imaging, Washington, America, pp. 289-293, (2018)

[8]

Han C., Murao K., Noguchi T., Et al., Learning more with less: conditional PGGAN-based data augmentation for brain metastases detection using highly-rough annotation on MR images, in: Proc. of the 28th ACM International Conference on Information and Knowledge Management (CIKM’19), pp. 119-127, (2019)

[9]

Redmon J., Farhadi A., YOLOv3: an Incremental Improvement

[10]

Zhu X.-Y., Liu Y.-F., Li J.-H., Wan T., Qin Z.-C., Emotion classification with data augmentation using generative adversarial network, Proc. Of the 22nd Pacific-Asia Conf. on Knowledge Discovery and Data Mining, Melbourne, Australia, pp. 349-360, (2018)

← 1 2 →