CoChat
Sign Up
Cited by 107Anomaly Detection Techniques and ApplicationsAdversarial Robustness in Machine LearningIndustrial Vision Systems and Defect Detection

Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection

Open access
Akcay, Samet, Atapour-Abarghouei, Amir, Breckon, Toby P.·2019·2019 International Joint Conference on Neural Networks (IJCNN)
DOI 10.1109/ijcnn.2019.8851808
Open this paper in CoChat — free accountOpen PDF

Abstract

Despite inherent ill-definition, anomaly detection is a research endeavour of great interest within machine learning and visual scene understanding alike. Most commonly, anomaly detection is considered as the detection of outliers within a given data distribution based on some measure of normality. The most significant challenge in real-world anomaly detection problems is that available data is highly imbalanced towards normality (i.e. non-anomalous) and contains at most a sub-set of all possible anomalous samples - hence limiting the use of well-established supervised learning methods. By contrast, we introduce an unsupervised anomaly detection model, trained only on the normal (non-anomalous, plentiful) samples in order to learn the normality distribution of the domain, and hence detect abnormality based on deviation from this model. Our proposed approach employs an encoder-decoder convolutional neural network with skip connections to thoroughly capture the multi-scale distribution of the normal data distribution in image space. Furthermore, utilizing an adversarial training scheme for this chosen architecture provides superior reconstruction both within image space and a lower-dimensional embedding vector space encoding. Minimizing the reconstruction error metric within both the image and hidden vector spaces during training aids the model to learn the distribution of normality as required. Higher reconstruction metrics during subsequent test and deployment are thus indicative of a deviation from this normal distribution, hence indicative of an anomaly. Experimentation over established anomaly detection benchmarks and challenging real-world datasets, within the context of X-ray security screening, shows the unique promise of such a proposed approach.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/ijcnn.2019.8851808

Cites

35 of 35 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Self-supervised learning with only positive pairs has resulted in competitive performance in comparison to contrastive learning which requires both negative pairs and positive pairs.

    “Self-supervised learning with only positive pairs [14], [16] has resulted in competitive performance in comparison to contrastive learning which requires both negative pairs and positive pairs [13], [17].”

    From Self-Supervised Learning for Anomaly Detection With Dynamic Local Augmentation (2021) · cites this paper as [13]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

5 of the 40 references couldn’t be matched to a known paper.

Research works printed but not linked: 4

  1. [4][4] V. Chandola, A. Banerjee, and V. Kumar, 'Anomaly detection,' ACM Computing Surveys , vol. 41, no. 3, pp. 1-58, jul 2009. I, II -
  2. [10][10] B. R. Kiran, D. M. Thomas, and R. Parakkal, 'An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos,' Journal of Imaging , vol. 4, no. 2, p. 36, 2018. I, II -
  3. [11][11] 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. 26722680. I, III-A1, III-C1 -
  4. [13][13] S. Akcay, A. Atapour-Abarghouei, and T. P. Breckon, 'Ganomaly: Semisupervised anomaly detection via adversarial training,' arXiv preprint arXiv:1805.06725 , 2018. I, II, III-B2, III-D, IV-A, IV-A3, IV-C, ?? , ?? - · arXiv

Cited by

Sorted by citations

Related

Authors
Akcay, S., Atapour-Abarghouei, A., & Breckon, T. P.
Affiliations
Durham University (GB)
ORCID
Breckon, Toby P.
Venue
2019 International Joint Conference on Neural Networks (IJCNN)
Publisher
IEEE
Published
2019-07
Pages
1-8
ISSN
2161-4407 (ISSN-L)
DOI
10.1109/ijcnn.2019.8851808
OpenAlex
W2911672077
Cited by
103
References
40
Citations by year
2025: 13 · 2024: 19 · 2023: 19 · 2022: 14 · 2021: 25 · 2020: 8 · 2019: 5
FWCI
4.97
Type
conference paper
Language
en
Open access
Licence
Locations
  • International Joint Conference on Neural Networks (IJCNN) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
  • Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
Keywords
anomaly detection, unsupervised anomaly detection, encoder-decoder architecture, skip connections, adversarial training, class imbalance, reconstruction error, X-ray security screening, image reconstruction

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