Generative adversarial networks for extrapolation of corrosion in automobile images

作者：

Highlights：

• Proposed an approach for generative adversarial networks using non-ideal datasets.

• Used a semi-supervised learning approach to compensate for small dataset size.

• Demonstrated the approach’s success by extrapolating corrosion in automobiles.

摘要

•Proposed an approach for generative adversarial networks using non-ideal datasets.•Used a semi-supervised learning approach to compensate for small dataset size.•Demonstrated the approach’s success by extrapolating corrosion in automobiles.

论文关键词：Generative adversarial neural networks,Deep learning under small datasets,Applied machine learning,Augmented reality applications

论文评审过程：Received 27 January 2022, Revised 14 September 2022, Accepted 14 September 2022, Available online 20 September 2022, Version of Record 6 October 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118849