ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomalies
Cited 3 time in scopus Download 9 time Share share facebook twitter linkedin kakaostory
Authors
Muhammad Zaigham Zaheer, Jin-Ha Lee, Arif Mahmood, Marcella Astrid, Seung-Ik Lee
Issue Date
2022-09
Citation
IEEE Transactions on Image Processing, v.31, pp.5963-5975
ISSN
1057-7149
Publisher
IEEE
Language
English
Type
Journal Article
DOI
https://dx.doi.org/10.1109/TIP.2022.3204217
Project Code
22HS1300, Development of AI Technology for Guidance of a Mobile Robot to its Goal with Uncertain Maps in Indoor/Outdoor Environments, Lee Jae-Yeong
Abstract
Recently, anomaly scores have been formulated using reconstruction loss of the adversarially learned generators and/or classification loss of discriminators. Unavailability of anomaly examples in the training data makes optimization of such networks challenging. Attributed to the adversarial training, performance of such models fluctuates drastically with each training step, making it difficult to halt the training at an optimal point. In the current study, we propose a robust anomaly detection framework that overcomes such instability by transforming the fundamental role of the discriminator from identifying real vs. fake data to distinguishing good vs. bad quality reconstructions. For this purpose, we propose a method that utilizes the current state as well as an old state of the same generator to create good and bad quality reconstruction examples. The discriminator is trained on these examples to detect the subtle distortions that are often present in the reconstructions of anomalous data. In addition, we propose an efficient generic criterion to stop the training of our model, ensuring elevated performance. Extensive experiments performed on six datasets across multiple domains including image and video based anomaly detection, medical diagnosis, and network security, have demonstrated excellent performance of our approach.
KSP Keywords
Adversarial Training, Current state, Medical diagnosis, Multiple domains, anomaly detection framework, excellent performance, network security, novelty detection, training data, video based