Few-Shot Anomaly Detection with Adversarial Loss for Robust Feature Representations
Jae Young Lee (KAIST),* Wonjun Lee (University of Science and Technology ), Jaehyun Choi (KAIST), Yongkwi LEE (ETRI), Young Seog Yoon (Electronics and Telecommunications Research Institute)
The 34th British Machine Vision Conference
Abstract
Anomaly detection is a critical and challenging task that aims to identify data points deviating from normal patterns and distributions within a dataset. Various methods have been proposed using a one-class-one-model approach, but these techniques often face practical problems such as memory inefficiency and the requirement of sufficient data for training. In particular, few-shot anomaly detection presents significant challenges in industrial applications, where limited samples are available before mass production. In this paper, we propose a few-shot anomaly detection method that integrates adversarial training loss to obtain more robust and generalized feature representations. We utilize the adversarial loss previously employed in domain adaptation to align feature distributions between source and target domains, to enhance feature robustness and generalization in few-shot anomaly detection tasks. We hypothesize that adversarial loss is effective when applied to features that should have similar characteristics, such as those from the same layer in a Siamese network's parallel branches or input-output pairs of reconstruction-based methods. Experimental results demonstrate that the proposed method generally achieves better performance when utilizing the adversarial loss.Video
Citation
@inproceedings{Lee_2023_BMVC,
author = {Jae Young Lee and Wonjun Lee and Jaehyun Choi and Yongkwi LEE and Young Seog Yoon},
title = {Few-Shot Anomaly Detection with Adversarial Loss for Robust Feature Representations},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0202.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by