AnomalyHop : An SSL-based Image Anomaly Localization Method

Zhang, Kaitai; Wang, Bin; Wang, Wei; Sohrab, Fahad; Gabbouj, Moncef; Kuo, C. C.Jay (2021-01-19)
 
Avaa tiedosto
Lataukset: 



Zhang, Kaitai
Wang, Bin
Wang, Wei
Sohrab, Fahad
Gabbouj, Moncef
Kuo, C. C.Jay
IEEE
19.01.2021


2021 International Conference on Visual Communications and Image Processing, VCIP 2021 - Proceedings
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited
doi:10.1109/VCIP53242.2021.9675385
Näytä kaikki kuvailutiedot
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tuni-202210267860

Kuvaus

Peer reviewed
Tiivistelmä
An image anomaly localization method based on the successive subspace learning (SSL) framework, called Anomaly-Hop, is proposed in this work. AnomalyHop consists of three modules: 1) feature extraction via successive subspace learning (SSL), 2) normality feature distributions modeling via Gaussian models, and 3) anomaly map generation and fusion. Comparing with state-of-the-art image anomaly localization methods based on deep neural networks (DNNs), AnomalyHop is mathematically transparent, easy to train, and fast in its inference speed. Besides, its area under the ROC curve (ROC-AUC) performance on the MVTec AD dataset is 95.9%, which is among the best of several benchmarking methods.
Kokoelmat