Conference paper Open Access

Towards Visual Anomaly Detection in Domains with Limited Amount of Labeled Data

Štepec, Dejan; Skočaj, Danijel

Anomaly detection in visual data refers to the problem of differentiating abnormal appearances from normal cases. Supervised approaches have been successfully applied to different domains, but require abundance of labeled data. Due to the nature of how anomalies occur and their underlying generating processes, it is hard to characterize and label them. Recent advances in deep generative based models have sparked interest towards applying such methods for unsupervised anomaly detection and have shown promising results in medical and industrial inspection domains.

Files (13.5 MB)
Name Size
ROSUS_2020_paper.pdf
md5:d93be12cc55d41331c5ded4747e8ecdc
13.5 MB Download
17
17
views
downloads
Views 17
Downloads 17
Data volume 229.1 MB
Unique views 15
Unique downloads 16

Share

Cite as