Anomaly-GAN: A data augmentation method for train surface anomaly detection

Train surface anomaly detection is an essential task in vision-based railway safety inspection. Although existing deep learning methods show great potential, their anomaly detection accuracy is affected by the lack of abnormal images. The number of abnormal images on the train surface is far less than that of normal images. One effective way to solve this problem is to expand the abnormal sample. However, most of train surface anomaly image generation methods faces difficulties in producing images with high quality and rich diversity at the same time. In addition, generating small-area anomalies is not ideal. An Anomaly-GAN based on mask pool, abnormal aware loss, and local versus global discriminators is thus proposed in this paper to solve these problems. The mask pool consists of prior-knowledge-based masks and expert-experience-based masks that guide model in generating anomalies with different shapes, rotation angles, spatial locations, and part numbers. The anomaly aware loss focuses on small-area anomalies, thereby promoting the generated anomalies with more detailed textures and richer semantics. The local versus global consistency discriminators combine local and global feature expressions that lead to the generation of more realistic and natural abnormal samples. The experiments show that, compared with other advanced data augmentation algorithms, the images generated by Anomaly-GAN achieve the best FID and LPIPS scores in all anomaly categories. In addition, compared with the case without data augmentaion, the proposed data enhancement method improves the performance of CNN on mAP and mIOU by 25.6% and 24.2%, respectively. Test code is available in https://github.com/AI-Dream-Chaser/Anomaly-GAN.