The DOI matches its Crossref record; 35 of the 40 references it cites were found in a registry or an index.
Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection
Open accessAbstract
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.
Overview
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
Verification
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.
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?
In the citing paper
“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.
Citations
Cites
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 2×
“The training objective L from Equation 4 is optimized via Adam [34] optimizer with an initial learning rate lr = 2e−3 with a lambda decay, and momentums β1 = 0.”
MethodInfluentialBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 1×
“An innovative and seminal work of Radford and Chintala [23] pioneered a new approach to stabilize GAN training by using fullyconvolutional layers and batch normalization [24] throughout the network.”
BackgroundGAN（Generative Adversarial Nets）
淳司, 柴. (2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 20,507
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftPreprint
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 15,273
Unsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235 · cited 3×
“The network architecture of the discriminator D follows the same structure as the discriminator of the DCGAN approach presented in [23].”
BackgroundChandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687
(2017) · Cited by 11,625
Conditional Generative Adversarial Nets
Mirza, M., & Osindero, S. (2014) · arXiv · doi:10.48550/arxiv.1411.1784 · Cited by 8,863 · cited 1×
“Training AAE provides superior reconstruction as well as the capability of controlling the latent space [20], [27], [28].”
BackgroundImproved Techniques for Training GANs
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016) · arXiv · doi:10.48550/arxiv.1606.03498 · Cited by 6,965 · cited 1×
“Recently, there has been a surge of interest in addressing the instability issues via several empirical methodologies [21], [22].”
BackgroundImproved training of Wasserstein GANs
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. (2017) · arXiv · doi:10.48550/arxiv.1704.00028 · Cited by 6,800 · cited 1×
“Another well-known attempt to stabilize GAN training is the use of Wasserstein loss in the training objective, which significantly improves training stability [25], [26].”
Method(2017) · International Conference on Machine Learning · Cited by 6,382
Generative Adversarial Networks: An Overview
Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., & Bharath, A. A. (2018) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2765202 · Cited by 4,540 · cited 1×
“Training AAE provides superior reconstruction as well as the capability of controlling the latent space [20], [27], [28].”
BackgroundA Survey of Outlier Detection Methodologies
Hodge, V., & Austin, J. (2004) · Artificial Intelligence Review · doi:10.1007/s10462-004-4304-y · Cited by 3,596
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial NetsPreprint
Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., & Abbeel, P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.03657 · Cited by 3,557 · cited 1×
“3) Inference within GAN: A strong correlation has been demonstrated between the manipulation of the input noise vector and the output of the generator network [23], [29].”
BackgroundUnsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
Schlegl, T., Seeböck, P., Waldstein, S. M., Schmidt-Erfurth, U., & Langs, G. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-59050-9_12 · Cited by 2,627
Towards Principled Methods for Training Generative Adversarial NetworksPreprint
Arjovsky, M., & Bottou, L. (2017) · International Conference on Learning Representations · doi:10.48550/arxiv.1701.04862 · Cited by 2,373 · cited 1×
“Recently, there has been a surge of interest in addressing the instability issues via several empirical methodologies [21], [22].”
BackgroundA survey of network anomaly detection techniques
Ahmed, M., Mahmood, A. N., & Hu, J. (2015) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2015.11.016 · Cited by 1,995
Adversarial Feature LearningPreprint
Donahue, J., Krähenbühl, P., & Darrell, T. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.09782 · Cited by 1,662 · cited 3×
“[12] investigate the use of BiGAN [18] in an anomaly detection task, examining joint training to map from image space to latent space simultaneously, and viceversa.”
BackgroundMethodPimentel, 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 · cited 2×
“Recently, the existing literature within the field has grown considerably, leading to a proliferation of taxonomy papers [1]–[5].”
BackgroundMakhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., & Frey, B. (2015) · arXiv · doi:10.48550/arxiv.1511.05644 · Cited by 1,579 · cited 1×
“Training AAE provides superior reconstruction as well as the capability of controlling the latent space [20], [27], [28].”
BackgroundNovelty detection: a review—part 1: statistical approaches
Markou, M., & Singh, S. (2003) · Signal Processing · doi:10.1016/j.sigpro.2003.07.018 · Cited by 1,472 · cited 2×
“Recently, the existing literature within the field has grown considerably, leading to a proliferation of taxonomy papers [1]–[5].”
BackgroundAdversarially Learned InferencePreprint
Dumoulin, V., Belghazi, M. I., Poole, B., Mastropietro, O., Lamb, A., Arjovsky, M., & Courville, A. C. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.00704 · Cited by 1,259 · cited 1×
“the former maps images to latent space, while the latter maps this latent space representation back into image space [32].”
BackgroundFraud detection system: A survey
Abdallah, A., Maarof, M. A., & Zainal, A. B. (2016) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2016.04.007 · Cited by 840 · cited 1×
“A significant body of prior work exists within anomaly detection for visual scene understanding [1]–[5] with a wide range of application domains [6]–[10].”
BackgroundNovelty detection: a review—part 2:
Markou, M., & Singh, S. (2003) · Signal Processing · doi:10.1016/j.sigpro.2003.07.019 · Cited by 813
Adversarially Learned One-Class Classifier for Novelty Detection
Sabokrou, M., Khalooei, M., Fathy, M., & Adeli, E. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00356 · Cited by 765
GANomaly: Semi-supervised Anomaly Detection via Adversarial Training
Akçay, S., Atapour–Abarghouei, A., & Breckon, T. P. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20893-6_39 · Cited by 706
Self-citationA survey of anomaly detection techniques in financial domain
Ahmed, M., Mahmood, A. N., & Islam, R. (2015) · Future Generation Computer Systems · doi:10.1016/j.future.2015.01.001 · Cited by 553
Efficient GAN-Based Anomaly DetectionPreprint
Zenati, H., Foo, C.-S., Lecouat, B., Manek, G., & Chandrasekhar, V. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.06222 · Cited by 517 · cited 10×
“to perform inference within the latent space is one of the novel contributions of the proposed approach compared to the previous approaches [9], [12], [13].”
BackgroundMethodResultInfluentialAUC: a statistically consistent and more discriminating measure than accuracy
Ling, C. X., Huang, J., & Zhang, H. (2003) · Cited by 501
Akçay, S., Kundegorski, M. E., Willcocks, C. G., & Breckon, T. P. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2018.2812196 · Cited by 393 · cited 1×
“In the context of X-ray baggage screening applications [33], the UBA and FFOB datasets from [13] are used to formulate an anomaly detection problem based on the concept of weapon threat items being an anomaly within the security screening process.”
MethodSelf-citationInverting the Generator of a Generative Adversarial Network
Creswell, A., & Bharath, A. A. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2875194 · Cited by 332
(2024) · TIB Data Manager · doi:10.57702/h8wosv5j · Cited by 202
Precise Recovery of Latent Vectors from Generative Adversarial NetworksPreprint
Lipton, Z. C., & Tripathi, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.04782 · Cited by 91 · cited 1×
“One approach to finding the optimal latent vectors is to create similar images is to inversely map images back to their hidden space via their gradients [31].”
BackgroundInverting The Generator Of A Generative Adversarial Network (II)Preprint
Creswell, A., & Bharath, A. A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.05701 · Cited by 23 · cited 1×
“Similar latent space variables have demonstrably produced visually similar high-resolution images [30].”
Background
Research works printed but not linked: 3
- 10.3390/jimaging4020036 · DOI
- goodfellow, 2014, Generative adversarial nets, Advances in neural information processing systems, 2672
- 10.1023/B:AIRE.0000045502.10941.a9 · DOI · Paper page
Cited by
Sorted by citations
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
DRÆM – A discriminatively trained reconstruction embedding for surface anomaly detection
Zavrtanik, V., Kristan, M., & Skocaj, D. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00822 · Cited by 1,086
“Reconstructive methods, such as Autoencoders [5, 1, 2, 26] and GANs [24, 23], have been extensively explored since they enable learning of a powerful reconstruction sub-space, using only anomaly-free images.”
BackgroundMethodInfluentialGAN-based anomaly detection: A review
Xia, X., Pan, X., Li, N., He, X., Ma, L., Zhang, X., & Ding, N. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.12.093 · Cited by 423
Graph Embedded Pose Clustering for Anomaly Detection
Markovitz, A., Sharir, G., Friedman, I., Zelnik-Manor, L., & Avidan, S. (2019) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr42600.2020.01055 · Cited by 222
Jiang, T., Li, Y., Xie, W., & Du, Q. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2965961 · Cited by 209
Metadata
- 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)
- 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
- green
- arxiv.org
- 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
