Gaussian Anomaly Detection by Modeling the Distribution of Normal Data in Pretrained Deep Features
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Anomaly detection (AD) in images is a fundamental computer vision problem and refers to identifying images that deviate significantly from normality. State-of-the-art AD algorithms commonly learn a model of normality from scratch using task-specific datasets in either semisupervised or self-supervised manner. We follow an alternative approach and model the distribution of normal data in deep feature representations learned from ImageNet via a multivariate Gaussian (MVG). This lightweight approach achieves a new state of the art in AD on the public MVTec AD dataset. In addition to the empirical benefits, we give a clear motivation for the seemingly simplistic approach via the ties between deep generative and discriminative modeling revealed recently. We further elucidate why ImageNet representations are discriminative in the transfer learning AD setting using the principal component analysis. Here, we find that the principal components containing little variance in normal data are the ones crucial for discriminating between normal and anomalous instances, giving an explanation for the unreasonable effectiveness of our approach. We also investigate setting the working point of our approach by selecting acceptable false-positive rate thresholds based on the MVG assumption and the resistance of our approach to unlabeled anomalies in the dataset. Finally, we investigate whether our approach is prone to exploiting spurious correlations using explainable AI techniques. Code is publicly available at https://github.com/ORippler/gaussian-ad-mvtec.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687
Estimating the Support of a High-Dimensional Distribution
Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C. (2001) · Neural Computation · doi:10.1162/089976601750264965 · Cited by 6,168
A well-conditioned estimator for large-dimensional covariance matrices
Ledoit, O., & Wolf, M. (2004) · Journal of Multivariate Analysis · doi:10.1016/s0047-259x(03)00096-4 · Cited by 3,046
Learning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., & Kundaje, A. (2017) · arXiv · doi:10.48550/arxiv.1704.02685 · Cited by 2,761
A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
Lee, K., Lee, K., Lee, H., & Shin, J. (2018) · arXiv · doi:10.48550/arxiv.1807.03888 · Cited by 2,450
Searching for activation functions
Ramachandran, P., Zoph, B., & Le, Q. V. (2017) · arXiv · doi:10.48550/arxiv.1710.05941 · Cited by 2,335
MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
Bergmann, P., Fauser, M., Sattlegger, D., & Steger, C. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00982 · Cited by 2,203
Pimentel, M. A. F., Clifton, D. A., Clifton, L., & Tarassenko, L. (2014) · Signal Processing · doi:10.1016/j.sigpro.2013.12.026 · Cited by 1,649
PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization
Defard, T., Setkov, A., Loesch, A., & Audigier, R. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-68799-1_35 · Cited by 1,415
Do Better ImageNet Models Transfer Better?
Kornblith, S., Shlens, J., & Le, Q. V. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00277 · Cited by 1,325
Uninformed Students: Student-Teacher Anomaly Detection With Discriminative Latent Embeddings
Bergmann, P., Fauser, M., Sattlegger, D., & Steger, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00424 · Cited by 990
Deep Anomaly Detection with Outlier Exposure
Hendrycks, D., Mazeika, M., & Dietterich, T. (2018) · arXiv · doi:10.48550/arxiv.1812.04606 · Cited by 932
Patch SVDD: Patch-Level SVDD for Anomaly Detection and Segmentation
Yi, J., & Yoon, S. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-69544-6_23 · Cited by 551
Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows
Rudolph, M., Wandt, B., & Rosenhahn, B. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00195 · Cited by 489
Deep Semi-Supervised Anomaly Detection
Ruff, L., Vandermeulen, R. A., Görnitz, N., Binder, A., Müller, E., Müller, K.-R., & Kloft, M. (2019) · arXiv · doi:10.48550/arxiv.1906.02694 · Cited by 388
Sub-Image Anomaly Detection with Deep Pyramid Correspondences
Cohen, N., & Hoshen, Y. (2020) · arXiv · doi:10.48550/arxiv.2005.02357 · Cited by 372
An Unsupervised-Learning-Based Approach for Automated Defect Inspection on Textured Surfaces
Mei, S., Yang, H., & Yin, Z. (2018) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2018.2795178 · Cited by 308
Attention Guided Anomaly Localization in Images
Venkataramanan, S., Peng, K.-C., Singh, R. V., & Mahalanobis, A. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58520-4_29 · Cited by 247
Explainable Deep One-Class Classification
Liznerski, P., Ruff, L., Vandermeulen, R. A., Franks, B. J., Kloft, M., & Müller, K.-R. (2020) · arXiv · doi:10.48550/arxiv.2007.01760 · Cited by 185
Cited by
Towards Total Recall in Industrial Anomaly Detection
Roth, K., Pemula, L., Zepeda, J., Scholkopf, B., Brox, T., & Gehler, P. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01392 · Cited by 1,810
Anomaly Detection via Reverse Distillation from One-Class Embedding
Deng, H., & Li, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00951 · Cited by 892
Surface Defect Detection Methods for Industrial Products: A Review
Chen, Y., Ding, Y., Zhao, F., Zhang, E., Wu, Z., & Shao, L. (2021) · Applied Sciences · doi:10.3390/app11167657 · Cited by 457
Deep Industrial Image Anomaly Detection: A Survey
Liu, J., Xie, G., Wang, J., Li, S., Wang, C., Zheng, F., & Jin, Y. (2024) · Machine Intelligence Research · doi:10.1007/s11633-023-1459-z · Cited by 463
Informative knowledge distillation for image anomaly segmentation
Cao, Y., Wan, Q., Shen, W., & Gao, L. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.108846 · Cited by 130
Metadata
- Authors
- Rippel, O., Mertens, P., Konig, E., & Merhof, D.
- Venue
- IEEE Transactions on Instrumentation and Measurement
- Published
- 2021
- Volume
- 70
- Pages
- 1-13
- ISSN
- 0018-9456 (ISSN-L)
- 1557-9662
- OpenAlex
- W3194400333
- Cited by
- 82
- References
- 23
- FWCI
- 5.47
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.