Citation

Zhendong H, Xiangyang G, Zhiyuan L, Xiaoyu A, Anping Z. Front. Neurorobotics 2024; 18: e1397369.

Copyright

(Copyright © 2024, Frontiers Research Foundation)

DOI

10.3389/fnbot.2024.1397369

PMID

38654752

PMCID

PMC11036376

Abstract

Rail surface defects present a significant safety concern in railway operations. However, the scarcity of data poses challenges for employing deep learning in defect detection. This study proposes an enhanced ACGAN augmentation method to address these issues. Residual blocks mitigate vanishing gradient problems, while a spectral norm regularization-constrained discriminator improves stability and image quality. Substituting the generator's deconvolution layer with upsampling and convolution operations enhances computational efficiency. A gradient penalty mechanism based on regret values addresses gradient abnormality concerns. Experimental validation demonstrates superior image clarity and classification accuracy compared to ACGAN, with a 17.6% reduction in FID value. MNIST dataset experiments verify the model's generalization ability. This approach offers practical value for real-world applications.

Language: en

Keywords

ACGAN; data enhancement; gradient punishment; residual block; spectral norm regularization