Few-Shot Anomaly Detection on Industrial Images through Contrastive Fine-Tuning

Jingyi Liao, Xun Xu, Manh Cuong Nguyen, Chuan-Sheng FooICLR 2023 · OpenReview

Abstract

Detecting abnormal products through imagery data is essential to the quality control in manufacturing. Existing approaches towards anomaly detection~(AD) often rely on substantial amount of anomaly-free samples to train representation and density models. Nevertheless, large anomaly-free datasets may not always be available before inference stage and this requires building an anomaly detection framework with only a handful of normal samples, a.k.a. few-shot anomaly detection (FSAD). We propose two techniques to address the challenges in FSAD. First, we employ a model pretrained on large source dataset to initialize model weights. To ameliorate the covariate shift between source and target domains, we adopt contrastive training on the few-shot target domain data. Second, to encourage learning representations suitable for downstream AD, we further incorporate cross-instance pairs to increase tightness within normal sample cluster and better separation between normal and synthesized negative samples. Extensive evaluations on six few-shot anomaly detection benchmarks demonstrate the effectiveness of the proposed method.
BibTeX
@inproceedings{liao2023few,
  author = {Jingyi Liao and Xun Xu and Manh Cuong Nguyen and Chuan-Sheng Foo},
  title = {{Few-Shot Anomaly Detection on Industrial Images through Contrastive Fine-Tuning}},
  booktitle = {International Conference on Learning Representations},
  year = {2023},
  url = {https://openreview.net/forum?id=iV0r9898C-},
}
Figure