ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article PseudoBound: Limiting the Anomaly Reconstruction Capability of One-Class Classifiers Using Pseudo Anomalies
Cited 15 time in scopus Download 46 time Share share facebook twitter linkedin kakaostory
Authors
Marcella Astrid, Muhammad Zaigham Zaheer, Seung-Ik Lee
Issue Date
2023-05
Citation
Neurocomputing, v.534, pp.147-160
ISSN
0925-2312
Publisher
Elsevier BV
Language
English
Type
Journal Article
DOI
https://dx.doi.org/10.1016/j.neucom.2023.03.008
Abstract
Due to the rarity of anomalous events, video anomaly detection is typically approached as one-class classification (OCC) problem. Typically in OCC, an autoencoder (AE) is trained to reconstruct the normal only training data with the expectation that, in test time, it can poorly reconstruct the anomalous data. However, previous studies have shown that, even trained with only normal data, AEs can often reconstruct anomalous data as well, resulting in a decreased performance. To mitigate this problem, we propose to limit the anomaly reconstruction capability of AEs by incorporating pseudo anomalies during the training of an AE. Extensive experiments using five types of pseudo anomalies show the robustness of our training mechanism towards any kind of pseudo anomaly. Moreover, we demonstrate the effectiveness of our proposed pseudo anomaly based training approach against several existing state-of-the-art (SOTA) methods on three benchmark video anomaly datasets, outperforming all the other reconstruction-based approaches in two datasets and showing the second best performance in the other dataset.
KSP Keywords
Anomaly based, Best performance, One-class classifiers, Test Time, existing state, one-class classification, state-of-The-Art, training data, video anomaly detection
This work is distributed under the term of Creative Commons License (CCL)
(CC BY NC ND)
CC BY NC ND