Anomaly Detection By Autoencoder Based On Weighted Frequency Domain Loss
This work addresses the issue of degraded anomaly detection accuracy in image analysis for applications like industrial inspection, though it is incremental as it builds on existing autoencoder methods.
The paper tackled the problem of insufficient reconstruction accuracy in autoencoder-based image anomaly detection by introducing a weighted frequency domain loss (WFDL) to improve high-frequency component reconstruction, resulting in improved anomaly detection accuracy as demonstrated by AUROC comparisons on the MVTec AD dataset.
In image anomaly detection, Autoencoders are the popular methods that reconstruct the input image that might contain anomalies and output a clean image with no abnormalities. These Autoencoder-based methods usually calculate the anomaly score from the reconstruction error, the difference between the input image and the reconstructed image. On the other hand, the accuracy of the reconstruction is insufficient in many of these methods, so it leads to degraded accuracy of anomaly detection. To improve the accuracy of the reconstruction, we consider defining loss function in the frequency domain. In general, we know that natural images contain many low-frequency components and few high-frequency components. Hence, to improve the accuracy of the reconstruction of high-frequency components, we introduce a new loss function named weighted frequency domain loss(WFDL). WFDL provides a sharper reconstructed image, which contributes to improving the accuracy of anomaly detection. In this paper, we show our method's superiority over the conventional Autoencoder methods by comparing it with AUROC on the MVTec AD dataset.