# Railway Anomaly detection model using synthetic defect images generated by CycleGAN

arXiv: https://arxiv.org/abs/2102.12595 · HTML: https://mlsanity.com/paper/2102.12595/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 5 references that are in the map.
- First posted on arXiv 24 Feb 2021.

## Builds on (most cited first, 2 of 2)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)

## Built on by (most cited first, 2 of 2)

- [Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey](https://mlsanity.com/paper/2207.10298/) (2022)
- [Synthetic Defect Generation for Display Front-of-Screen Quality Inspection: A Survey](https://mlsanity.com/paper/2203.03429/) (2022)

## Abstract (arXiv)

Although training data is essential for machine learning, railway companies are facing difficulties in gathering adequate images of defective equipment due to their proactive replacement of would be defective equipment. Nevertheless, proactive replacement is indispensable for safe and undisturbed operation of public transport. In this research, we have developed a model using CycleGAN to generate artificial images of defective equipment instead of real images. By adopting these generated images as training data, we verified that these images are indistinguishable from real images and they play a vital role in enhancing the accuracy of the defect detection models.