A Multi-Scale A Contrario method for Unsupervised Image Anomaly Detection
Open accessAbstract
Anomalies can be defined as any non-random structure which deviates from normality. Anomaly detection methods reported in the literature are numerous and diverse, as what is considered anomalous usually varies depending on particular scenarios and applications. In this work we propose an a contrario framework to detect anomalies in images applying statistical analysis to feature maps obtained via convolutions. We evaluate filters learned from the image under analysis via patch PCA and the feature maps obtained from a pre-trained deep neural network (Resnet). The proposed method is multi-scale and fully unsupervised, and is able to detect anomalies in a wide variety of scenarios. While the end goal of this work is the detection of subtle defects in leather samples for the automotive industry, we show that the same algorithm achieves state-of-the-art results in public anomalies datasets.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 28 · Cited by 10
Research works printed but not linked: 4
- M. M. Moya, M. W. Koch, and L. D. Hostetler, "One-class classifier networks for target recognition applications," NASA STI/Recon Technical Report N, vol. 93, p. 24043, 1993.
- T. Ehret, A. Davy, M. Delbracio, and J.-M. Morel, "How to reduce anomaly detection in images to anomaly detection in noise," Image Processing On Line, vol. 9, pp. 391-412, 2019.
- L. Ruff, R. Vandermeulen, N. Goernitz, L. Deecke, S. A. Siddiqui, A. Binder, E. Müller, and M. Kloft, "Deep one-class classification," in International conference on machine learning. PMLR, 2018, pp. 4393-4402.
- I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative adversarial nets," in Advances in neural information processing systems, 2014, pp. 2672- 2680.
- Authors
- Tailanian, M., Muse, P., & Pardo, A.
- Venue
- 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)
- Publisher
- IEEE
- Published
- 2021-12
- Pages
- 179-184
- OpenAlex
- W3204890627
- Cited by
- 10
- References
- 28
- Citations by year
- 2026: 1 · 2025: 4 · 2024: 4 · 2022: 1
- FWCI
- 0.57
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- International Conference on Machine Learning and Applications (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- Agencia Nacional de Investigación e Innovación
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
- Keywords
- image anomaly detection, unsupervised anomaly detection, multiscale analysis, feature maps, pre-trained deep neural networks, ResNet, leather defect detection, automotive industry
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
