FAGAN ：AN ADVERSARIAL GENERATION METHOD OF SOLAR CELLS DEFECT IMAGE BASED ON MODEL TRANSFER AND ATTENTION MECHANISM

被引：0
|
作者：
Sun L. [1 ]
Mao J. [2 ]
Liu K. [1 ]
机构：
[1] School ofArtificial Intelligence, Hebei University of Technology, Tianjin
[2] Guodian United Power Technology Co.，Ltd., Beijing
来源：
Taiyangneng Xuebao/Acta Energiae Solaris Sinica | 2023年 / 44卷 / 09期
关键词：
attention; convolutional neural networks; generative adversarial network; image processing; solar cells; transfer learning;
D O I：
10.19912/j.0254-0096.tynxb.2022-0754
中图分类号：
学科分类号：
摘要：
Small and weak defects and insufficient dataset are the bottlenecks problems which restrict the rapid development of solar cells quality detection technology. Therefore，this paper proposes FAGAN for generating defect images of solar cells. This method firstly performs model pre-training on the source domain open road dataset to extract cross-domain underlying visual features，so as to improve the diversity of defect forms generated by FAGAN on the target domain；then，ECSA is designed to enhance the defect features in two dimensions of space and channel，so as to improve the quality of small and weak defect samples. The experiments show that the FID of the solar cell defect images generated by the proposed method is better than those of the existing gradient penalty Wasserstein distance generative adversarial network（WGAN-GP），deep convolution generative adversarial network（DCGAN），cycle generative adversarial network（CycleGAN）and style generative adversarial network（StyleGAN）. © 2023 Science Press. All rights reserved.
引用
收藏
页码：78 / 84
页数：6
相关论文
共 13 条
  • [1] LI Q, LIU B, Et al., Bird droppings coverage detection of photovoltaic module based on transfer learning ［J］, Acta energiae solaris sinica, 43, 2, pp. 233-237, (2022)
  • [2] ZHONG Z，, ZHENG L，, KANG G L，, Et al., Random erasing data augmentation, Proceedings of the AAAI Conference on Artificial Intelligence, (2020)
  • [3] ZHANG H Y, DAUPHIN Y N，, Et al., Mixup：beyond empirical risk minimization, International Conference on Learning Representations, (2018)
  • [4] Generative adversarial networks, Proceedings of the 27th International Conference on Neural Information Processing Systems, (2014)
  • [5] WANG X G，, Et al., Region-and strength-controllable GAN for defect generation and segmentation in industrial images［J］, IEEE transactions on industrial informatics, 18, 7, pp. 4531-4541, (2022)
  • [6] WANG X G，, Et al., Defect image sample generation with GAN for improving defect recognition［J］, IEEE transactions on automation science and engineering, 17, 3, pp. 1611-1622, (2020)
  • [7] WANG Y X, GONZALEZ-GARCIA A, MineGAN： effective knowledge transfer from GANs to target domains with few images, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）, pp. 9332-9341, (2020)
  • [8] ZHANG H, Et al., Self-attention generative adversarial networks［C］, International Conference on Machine Learning, pp. 7354-7363, (2019)
  • [9] WANG J Y, ZHANG C G，, YANG H T，, Et al., Satellite image translation method based on attention residual network［J］, Laser & optoelectronics progress, 59, 2, pp. 232-242, (2022)
  • [10] ZHU J Y, ISOLA P，, Et al., Unpaired image- to-image translation using cycle- consistent adversarial networks, 2017 IEEE International Conference on Computer Vision（ICCV）, pp. 2223-2232, (2017)
12