Liao, J., Xu, X., Nguyen, M. C., Goodge, A., & Foo, C. S. (2024). COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detection. IEEE Transactions on Image Processing, 33, 2090–2103. https://doi.org/10.1109/tip.2024.3374048
Abstract:
Existing approaches towards anomaly detection (AD) often rely on a substantial amount of anomaly-free data to train representation and density models. However, large anomaly-free datasets may not always be available before the inference stage; in which case an anomaly detection model must be trained with only a handful of normal samples, a.k.a. fewshot anomaly detection (FSAD). In this paper, we propose a novel methodology to address the challenge of FSAD which incorporates two important techniques. Firstly, we employ a model pre-trained on a large source dataset to initialize model weights. Secondly, to ameliorate the covariate shift between source and target domains, we adopt contrastive training to fine-tune on the few-shot target domain data. To learn suitable representations for the downstream AD task, we additionally incorporate cross-instance positive pairs to encourage a tight cluster of the normal samples, and negative pairs for better separation between normal and synthesized negative samples. We evaluate few-shot anomaly detection on on 3 controlled AD tasks and 4 real-world AD tasks to demonstrate the effectiveness of the proposed method.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research - AME Programmatic Funds
Grant Reference no. : A20H6b0151