Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection (2312.15911v1)
Abstract: Recent unsupervised anomaly detection methods often rely on feature extractors pretrained with auxiliary datasets or on well-crafted anomaly-simulated samples. However, this might limit their adaptability to an increasing set of anomaly detection tasks due to the priors in the selection of auxiliary datasets or the strategy of anomaly simulation. To tackle this challenge, we first introduce a prior-less anomaly generation paradigm and subsequently develop an innovative unsupervised anomaly detection framework named GRAD, grounded in this paradigm. GRAD comprises three essential components: (1) a diffusion model (PatchDiff) to generate contrastive patterns by preserving the local structures while disregarding the global structures present in normal images, (2) a self-supervised reweighting mechanism to handle the challenge of long-tailed and unlabeled contrastive patterns generated by PatchDiff, and (3) a lightweight patch-level detector to efficiently distinguish the normal patterns and reweighted contrastive patterns. The generation results of PatchDiff effectively expose various types of anomaly patterns, e.g. structural and logical anomaly patterns. In addition, extensive experiments on both MVTec AD and MVTec LOCO datasets also support the aforementioned observation and demonstrate that GRAD achieves competitive anomaly detection accuracy and superior inference speed.
- Ganomaly: Semi-supervised anomaly detection via adversarial training. In ACCV.
- Variational Autoencoder based Anomaly Detection using Reconstruction Probability. In SNU Data Mining Center, Tech. Rep.
- Detecting anomalous data using auto-encoders. International Journal of Machine Learning and Computing, 6(1): 21.
- Towards principled methods for training generative adversarial networks. In International Conference on Learning Representations (ICLR).
- Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images. In BrainLes@MICCAI.
- Beyond dents and scratches: Logical constraints in unsupervised anomaly detection and localization. International Journal of Computer Vision, 130(4): 947–969.
- MVTec AD–A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection. In CVPR.
- Uninformed Students: Student-Teacher Anomaly Detection With Discriminative Latent Embeddings. In CVPR.
- The mvtec 3d-ad dataset for unsupervised 3d anomaly detection and localization. arXiv preprint arXiv:2112.09045.
- Deep One-Class Classification via Interpolated Gaussian Descriptor. In AAAI.
- Sub-Image Anomaly Detection with Deep Pyramid Correspondences. ArXiv, abs/2005.02357.
- GradPU: positive-unlabeled learning via gradient penalty and positive upweighting. In Proceedings of the AAAI Conference on Artificial Intelligence.
- PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization. In ICPR Workshops.
- ImageNet: A large-scale hierarchical image database. In CVPR.
- Attention is not all you need: Pure attention loses rank doubly exponentially with depth. In International Conference on Machine Learning, 2793–2803. PMLR.
- Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 1705–1714.
- Cflow-ad: Real-time unsupervised anomaly detection with localization via conditional normalizing flows. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 98–107.
- Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33: 6840–6851.
- Back to the feature: classical 3d features are (almost) all you need for 3d anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2967–2976.
- Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection. In ICCV.
- ReConPatch: Contrastive Patch Representation Learning for Industrial Anomaly Detection. arXiv preprint arXiv:2305.16713.
- An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos. Journal of Imaging, 4(2): 36.
- CutPaste: Self-Supervised Learning for Anomaly Detection and Localization. In CVPR.
- Explainable Deep One-Class Classification. In ICLR.
- Fully convolutional networks for semantic segmentation. In CVPR, 3431–3440.
- OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations. In CVPR.
- Generative Probabilistic Novelty Detection with Adversarial Autoencoders. In NeurIPS.
- Inpainting Transformer for Anomaly Detection. In ICIAP.
- Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection. In CVPR.
- Improving the adversarial robustness and interpretability of deep neural networks by regularizing their input gradients. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).
- Towards total recall in industrial anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 14318–14328.
- Same same but differnet: Semi-supervised defect detection with normalizing flows. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, 1907–1916.
- A primitive study on unsupervised anomaly detection with an autoencoder in emergency head CT volumes. In Medical Imaging 2018: Computer-Aided Diagnosis.
- Natural Synthetic Anomalies for Self-supervised Anomaly Detection and Localization. In ECCV.
- Set features for fine-grained anomaly detection. arXiv preprint arXiv:2302.12245.
- Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th international conference on Machine learning, 1096–1103.
- SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classification. arXiv preprint arXiv:2305.00398.
- Visual Anomaly Detection via Dual-Attention Transformer and Discriminative Flow. arXiv preprint arXiv:2303.17882.
- Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation. In ACCV.
- A Unified Model for Multi-class Anomaly Detection. In NeurIPS.
- Fastflow: Unsupervised anomaly detection and localization via 2d normalizing flows. arXiv preprint arXiv:2111.07677.
- Reconstruction by inpainting for visual anomaly detection. Pattern Recognit., 112: 107706.
- Dsr–a dual subspace re-projection network for surface anomaly detection. In European conference on computer vision, 539–554. Springer.
- DRAEM - A Discriminatively Trained Reconstruction Embedding for Surface Anomaly Detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 8330–8339.
- Prototypical residual networks for anomaly detection and localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16281–16291.
- One-Class Adversarial Nets for Fraud Detection. In AAAI.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.