| Paper ID | CI-4.5 |
| Paper Title |
FOURIER TRANSFORMATION AUTOENCODERS FOR ANOMALY DETECTION |
| Authors |
Demetris Lappas, Vasileios Argyriou, Dimitrios Makris, Kingston University, United Kingdom |
| Session | CI-4: Remote Sensing and Coded Aperture Imaging |
| Location | Gather.Town |
| Session Time: | Thursday, 10 June, 15:30 - 16:15 |
| Presentation Time: | Thursday, 10 June, 15:30 - 16:15 |
| Presentation |
Poster
|
| Topic |
Computational Imaging: [IMT] Computational Imaging Methods and Models |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Anomaly detection is a challenging problem, mainly due to the lack of a sufficient set of abnormal samples that represents every possible anomaly. Therefore unsupervised methods are employed to model normality and anomaly is detected as an outlier to such model. This paper introduces Fourier Transforms into AutoEncoders to demonstrate how the inclusion of a frequency domain presents less noisy features for a deep learning network to detect anomalies. Comparing our results to the state of the art on a variety of datasets, we show how the proposed method can provide competitive results. |
