English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In image anomaly detection, Autoencoders are the popular methods thatreconstruct the input image that might contain anomalies and output a cleanimage with no abnormalities. These Autoencoder-based methods usually calculatethe anomaly score from the reconstruction error, the difference between theinput image and the reconstructed image. On the other hand, the accuracy of thereconstruction is insufficient in many of these methods, so it leads todegraded accuracy of anomaly detection. To improve the accuracy of thereconstruction, we consider defining loss function in the frequency domain. Ingeneral, we know that natural images contain many low-frequency components andfew high-frequency components. Hence, to improve the accuracy of thereconstruction of high-frequency components, we introduce a new loss functionnamed weighted frequency domain loss(WFDL). WFDL provides a sharperreconstructed image, which contributes to improving the accuracy of anomalydetection. In this paper, we show our method's superiority over theconventional Autoencoder methods by comparing it with AUROC on the MVTec ADdataset.

Anomaly Detection By Autoencoder Based On Weighted Frequency Domain Loss