Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore

In the area of fewshot anomaly detection (FSAD), efficient visual feature plays an essential role in memory bank M-based methods. However, these methods do not account for the relationship between the visual feature and its rotated visual feature, drastically limiting the anomaly detection performance. To push the limits, we reveal that rotation-invariant feature property has a significant impact in industrial-based FSAD. Specifically, we utilize graph representation in FSAD and provide a novel visual isometric invariant feature (VIIF) as anomaly measurement feature. As a result, VIIF can robustly improve the anomaly discriminating ability and can further reduce the size of redundant features stored in M by a large amount. Besides, we provide a novel model GraphCore via VIIFs that can fast implement unsupervised FSAD training and can improve the performance of anomaly detection. A comprehensive evaluation is provided for comparing GraphCore and other SOTA anomaly detection models under our proposed fewshot anomaly detection setting, which shows GraphCore can increase average AUC by 5.8%, 4.1%, 3.4%, and 1.6% on MVTec AD and by 25.5%, 22.0%, 16.9%, and 14.1% on MPDD for 1, 2, 4, and 8-shot cases, respectively.

[1]  Michael W. Spratling,et al.  Registration based Few-Shot Anomaly Detection , 2022, ECCV.

[2]  Seunghyun Lee,et al.  CFA: Coupled-Hypersphere-Based Feature Adaptation for Target-Oriented Anomaly Localization , 2022, IEEE Access.

[3]  E. Wu,et al.  Vision GNN: An Image is Worth Graph of Nodes , 2022, NeurIPS.

[4]  Chunhua Shen,et al.  Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection* , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  C. Steger,et al.  Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization , 2022, International Journal of Computer Vision.

[6]  Xingyu Li,et al.  Anomaly Detection via Reverse Distillation from One-Class Embedding , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Radim Burget,et al.  Deep learning-based defect detection of metal parts: evaluating current methods in complex conditions , 2021, 2021 13th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT).

[8]  Tyng-Luh Liu,et al.  Learning Unsupervised Metaformer for Anomaly Detection , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[9]  Anton van den Hengel,et al.  Explainable Deep Few-shot Anomaly Detection with Deviation Networks , 2021, ArXiv.

[10]  B. Schölkopf,et al.  Towards Total Recall in Industrial Anomaly Detection , 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Errui Ding,et al.  Student-Teacher Feature Pyramid Matching for Anomaly Detection , 2021, BMVC.

[12]  Xiang Li,et al.  Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[13]  Romaric Audigier,et al.  PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization , 2020, ICPR Workshops.

[14]  Marius Kloft,et al.  Explainable Deep One-Class Classification , 2020, ICLR.

[15]  Yedid Hoshen,et al.  Sub-Image Anomaly Detection with Deep Pyramid Correspondences , 2020, ArXiv.

[16]  Guido Montúfar,et al.  Haar Graph Pooling , 2019, ICML.

[17]  Xiaosheng Zhuang,et al.  Fast Haar Transforms for Graph Neural Networks , 2019, Neural Networks.

[18]  Carsten Steger,et al.  MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[20]  Frank Hutter,et al.  Decoupled Weight Decay Regularization , 2017, ICLR.

[21]  Silvio Savarese,et al.  Active Learning for Convolutional Neural Networks: A Core-Set Approach , 2017, ICLR.

[22]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[23]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[24]  Koray Kavukcuoglu,et al.  Exploiting Cyclic Symmetry in Convolutional Neural Networks , 2016, ICML.

[25]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[26]  C. Steger,et al.  Anomaly Detection via Reverse Distillation from One-Class Embedding , 2022 .