Few-Shot Anomaly Detection with Adversarial Loss for Robust Feature Representations
This work addresses memory inefficiency and data scarcity issues in anomaly detection for industrial settings, but it is incremental as it adapts existing adversarial loss techniques to a new context.
The paper tackles the problem of few-shot anomaly detection in industrial applications by integrating adversarial training loss to enhance feature robustness and generalization, achieving generally better performance in experiments.
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.