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].”
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
Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection
Hou, J., Zhang, Y., Zhong, Q., Xie, D., Pu, S., & Zhou, H. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00867 · Cited by 213
“…positive rate with varying Method MNIST CIFAR10 VAE [21] 0.877 0.581 AnoGAN [42] 0.937 0.612 ADGAN [10] 0.947 0.624 GANomaly [1] 0.928 0.695 GeoTrans [13] 0.980 0.656 Skip-GANomaly [2] - 0.732 OCGAN [33] 0.975 0.656 MemAE 1 [14] 0.975 0.609 CAVGA-D u [45] 0.986 0.737 Ours 0.990 0.753 thresholds.”
InfluentialJežek, Š., Jonák, M., Bürget, R., Dvořák, P., & Skotak, M. (2021) · International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT) · doi:10.1109/icumt54235.2021.9631567 · Cited by 202
Tang, T., Kuo, W.-H., Lan, J.-H., Ding, C., Hsu, H., & Young, H. (2020) · Sensors · doi:10.3390/s20123336 · Cited by 149
Chan, R., Rottmann, M., & Gottschalk, H. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00508 · Cited by 147
Prototypical Residual Networks for Anomaly Detection and Localization
Zhang, H., Wu, Z., Wang, Z., Chen, Z., & Jiang, Y. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01562 · Cited by 129
“Auto-Encoder based methods [3,6,15,65] rely on the hypothesis that the model is trained to reconstruct normal regions well but fails for abnormal regions.”
Self-Supervised Masking for Unsupervised Anomaly Detection and Localization
Huang, C., Xu, Q., Wang, Y.-F., Wang, Y., & Zhang, Y. (2022) · IEEE transactions on multimedia · doi:10.1109/tmm.2022.3175611 · Cited by 110
“We compare the proposed SSM with several state-of-the-arts, including OCGAN [9], ALOCC [8], GeoTrans [17], DAE [42], MemAE [16], GANomaly [50], SCADN [22], ARNet [19], US [60] and MKD [63].”
BackgroundMethodCollin, A.-S., & De Vleeschouwer, C. (2021) · 2020 25th International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr48806.2021.9412842 · Cited by 106
“In the context of anomaly detection, some GAN-based solutions fail to exclude defective samples from the generative distribution [10] and require an extra optimization step in the latent space during inference [8].”
BackgroundMethodInfluentialLin, H., Liu, Y., Li, S., & Qu, X. (2023) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2023.123744 · Cited by 99
Learning Unsupervised Metaformer for Anomaly Detection
Wu, J.-C., Chen, D.-J., Fuh, C.-S., & Liu, T.-L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00433 · Cited by 91
“There are also several GAN-based approaches [2, 3, 7, 24, 25, 30] that apply adversarial training to enhance the performance of AD.”
BackgroundZhong, J., Xie, W., Li, Y., Lei, J., & Du, Q. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3013022 · Cited by 82
“…without noise prior is as feature extractor or applied in anomaly detection by the residual between the reconstructed background image and the original image, which means that anomalies are expected to have large reconstruction errors and the background has small reconstruction errors [30]–[32].”
BackgroundGAN Ensemble for Anomaly Detection
Xu, H., Chen, X., & Liu, L. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i5.16530 · Cited by 79
Video Anomaly Detection and Localization Based on an Adaptive Intra-Frame Classification Network
Xu, K., Sun, T., & Jiang, X. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2929931 · Cited by 73
Machine learning in NextG networks via generative adversarial networks
Ayanoglu, E., Davaslioglu, K., & Sagduyu, Y. E. (2022) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2022.3153004 · Cited by 55
Dual feature extraction network for hyperspectral image analysis
Xie, W., Lei, J., Fang, S., Li, Y., Jia, X., & Li, M. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.107992 · Cited by 55
3D-MMFN: Multi-level multimodal fusion network for 3D industrial image anomaly detection
Asad, M., Azeem, W., Malik, A. A., Jiang, H., Ali, A., Yang, J., & Liu, W. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103284 · Cited by 51
Wang, D., Xiao, H., & Wu, D. (2022) · NDT & E International · doi:10.1016/j.ndteint.2022.102766 · Cited by 39
Unsupervised Region-Based Anomaly Detection In Brain MRI With Adversarial Image Inpainting
Nguyen, B., Feldman, A., Bethapudi, S., Jennings, A., & Willcocks, C. G. (2021) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi48211.2021.9434115 · Cited by 39
“Following AnoGAN [2], other works [4, 5, 6] have improved upon instance anomaly detection and the computationally expensive mapping procedure.”
MethodInfluentialSelf-Supervised Learning for Anomaly Detection With Dynamic Local Augmentation
Yoa, S., Lee, S., Kim, C., & Kim, H. J. (2021) · IEEE Access · doi:10.1109/access.2021.3124525 · Cited by 38
Baydargil, H. B., Park, J.-S., & Kang, D.-Y. (2021) · Applied Sciences · doi:10.3390/app11052187 · Cited by 30
“The recent trend of anomaly detection models such as skip-GAN [56] and Anoma-lyGAN (AnoGAN) [23] is to train the model on the normal dataset by separating it into train-test fashion, and then perform inference with both unseen normal and unseen abnormal samples.”
MethodUnsupervised industrial anomaly detection with diffusion models
Xu, H., Xu, S., & Yang, W. (2023) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2023.103983 · Cited by 36
TDAD: Self-supervised industrial anomaly detection with a two-stage diffusion model
Wei, C., Han, H., Xia, Y., & Ji, Z. (2024) · Computers in Industry · doi:10.1016/j.compind.2024.104192 · Cited by 35
SAGAN: Skip-Attention GAN For Anomaly Detection
Liu, G., Lan, S., Zhang, T., Huang, W., & Wang, W. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506332 · Cited by 29
“Model AUC EGBAD [5] 0.489 GANomaly [6] 0.900 Skip-GANomaly [8] 0.840 SAGAN without DSCs 0.960 SAGAN with DSCs 0.958 Table 3 .”
MethodResultInfluentialMulti-scale GAN with transformer for surface defect inspection of IC metal packages
Chen, K., Cai, N., Wu, Z., Xia, H., Zhou, S., & Wang, H. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118788 · Cited by 29
MTDiff: Visual anomaly detection with multi-scale diffusion models
Wang, X., Li, W., & He, X. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112364 · Cited by 34
Template-based Feature Aggregation Network for industrial anomaly detection
Luo, W., Yao, H., & Yu, W. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107810 · Cited by 25
Two-stage coarse-to-fine image anomaly segmentation and detection model
Shah, R. A., Urmonov, O., & Kim, H. (2023) · Image and Vision Computing · doi:10.1016/j.imavis.2023.104817 · Cited by 21
Cloud-GAN: Cloud Generation Adversarial Networks for anomaly detection
Zeng, X., Zhuo, Y., Liao, T., & Guo, J. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110866 · Cited by 21
Unsupervised Two-Stage Anomaly DetectionPreprint
Liu, Y., Zhuang, C., & Lu, F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.11671 · Cited by 36
“Skip-GANomaly [3] replaces the auto-encoder with U-net [40] and further gets better reconstructions.”
BackgroundMethodInfluentialGeo-Hgan: Unsupervised anomaly detection in geochemical data via latent space learning
Ding, L., Chen, B., Zhu, Y., Dong, H., Chan, G., & Zhang, P. (2024) · Computers & Geosciences · doi:10.1016/j.cageo.2024.105703 · Cited by 18
Temporal Fusion Based Mutli-scale Semantic Segmentation for Detecting Concealed Baggage Threats
Shafay, M., Hassan, T., Damiani, E., & Werghi, N. (2021) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc52423.2021.9658932 · Cited by 17
“While many of the deep learning frameworks utilized supervised learning to detect cluttered baggage threats [12], researchers have also proposed semi-supervised [13], unsupervised schemes [14], [15] and tensor-pooling based frameworks [16] to recognize baggage threats as anomalies.”
Tail of Distribution GAN (TailGAN): GenerativeAdversarial-Network-Based Boundary Formation
Dionelis, N., Yaghoobi, M., & Tsaftaris, S. A. (2020) · Sensor Signal Processing for Defence (SSPD) · doi:10.1109/sspd47486.2020.9272100 · Cited by 17
Sun, T., Guo, B., Ruan, T., Zhou, X., bai, D., Yu, H., & Wang, Y. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127005 · Cited by 17
Visual Anomaly Detection for Images: A SurveyPreprint
Yang, J., Xu, R., Qi, Z., & Shi, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.13157 · Cited by 16
“Akc¸ay et al.[35] further introduce an encoder where the difference between the latent code of reconstructed image and the ones of the input image is also used as an indicator for the anomaly.”
MethodMulti-Task Learning based Video Anomaly Detection with Attention
Baradaran, M., & Bergevin, R. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00290 · Cited by 15
“Researchers have formulated anomaly detection as frame(s) reconstruction [1, 7, 11, 12, 14, 20] or as prediction tasks [3, 6, 16, 24, 26], assuming that the unsupervised network (e.”
BackgroundUnsupervised Detection of Cancerous Regions in Histology Imagery using Image-to-Image Translation
Štepec, D., & Skočaj, D. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00419 · Cited by 15
“Learning the normal visual appearance is based on autoencoders (AE) [6], generative adversarial networks (GAN) [20, 21], or combined hybrid models [1, 2] and was already investigated for the histology domain [22].”
BackgroundDMU-TransNet: Dense multi-scale U-shape transformer network for anomaly detection
Zhou, W., Wu, S., Wang, Y., Zuo, L., Yi, Y., & Cui, W. (2024) · Measurement · doi:10.1016/j.measurement.2024.114216 · Cited by 14
Bhowmik, N., Gaus, Y. F. A., & Breckon, T. P. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506608 · Cited by 14
“Semi-supervised adversarial learning is used in the works of [9, 10] for pro-hibited item detection.”
MethodSelf-citationPoyser, M., & Breckon, T. P. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111948 · Cited by 14
“In general, we find that contemporary state-of-the-art autoencoder architectures [39] employ skip-connections between the encoder and decoder sub-networks to facilitate improved image reconstruction.”
Self-citationA priori assessment of nonlocal data-driven wall modeling in large eddy simulation
Jamaat, G. T. (2023) · Physics of Fluids · doi:10.1063/5.0146770 · Cited by 13
A Novel GAN-based Fault Diagnosis Approach for Imbalanced Industrial Time SeriesPreprint
Jiang, W., Cheng, C., Zhou, B., Ma, G., & Yuan, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.00575 · Cited by 13
“To solve the imbalanced industrial data for fault diagnosis and preprocess the huge amount of time series before training the model, motivated by [1], [2], we propose a novel GAN[3]-”
BackgroundMethodHu, Y., He, N., Xie, L., Chen, D., Gao, C., & Ding, H. (2024) · NDT & E International · doi:10.1016/j.ndteint.2024.103050 · Cited by 12
Boundary Of Distribution Support Generator (BDSG): Sample Generation On The Boundary
Dionelis, N., Yaghoobi, M., & Tsaftaris, S. A. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9191341 · Cited by 11
“Existing approaches to anomaly detection use probability, reconstruction [5, 6], and domain based models.”
MethodIntrusion Detection for in-vehicle CAN Networks Based on Auxiliary Classifier GANs
Chen, M., Zhao, Q., Jiang, Z., & Xu, R. Y. (2021) · International Conference on High Performance Big Data and Intelligent Systems (HPBD&IS) · doi:10.1109/hpbdis53214.2021.9658465 · Cited by 10
Gaus, Y. F. A., Bhowmik, N., Akçay, S., Guillen-Garcia, P. M., Barker, J. W., & Breckon, T. P. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8851829 · Cited by 82
“In followup work, [31] proposes another unsupervised anomaly detection approach, whereby the use of skip connected layer design allows to train much higher resolution images and optimizing latent space within the discriminator network leads to significantly better results.”
BackgroundSelf-citationAdversarial Regularized Reconstruction for Anomaly Detection and Generation
Liguori, A., Manco, G., Pisani, F. S., & Ritacco, E. (2021) · Proceedings · doi:10.1109/icdm51629.2021.00145 · Cited by 9
Industrial Anomaly Detection with Skip Autoencoder and Deep Feature Extractor
Tang, T., Hsu, H., Huang, W.-R., & Li, K. (2022) · Sensors · doi:10.3390/s22239327 · Cited by 9
“The inference times of AnoGAN, GANomaly, Skip-GANomaly, and the proposed method are shown in Table 4.”
BackgroundMethodInfluentialHassan, T., Khan, S. H., Akçay, S., Bennamoun, M., & Werghi, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.04251 · Cited by 12
“Akcay et al. [23] proposed a Skip-GANomaly architecture for detecting different anomalies from x-ray scans.”
BackgroundAnomaly detection and segmentation in industrial images using multi-scale reverse distillation
Liu, C., & Chung, C.-C. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112502 · Cited by 9
Liu, S., Chen, J., Liu, Z., Wang, J., & Wang, Z. J. (2024) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2024.110784 · Cited by 9
Han, J., Chen, Z., Zhou, D., Hu, B., Xia, T., & Pan, E. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110298 · Cited by 8
Baggage Threat Detection Under Extreme Class Imbalance
Ahmed, A. H., Velayudhan, D., Hassan, T., Hassan, B., Dias, J. M. M., & Werghi, N. (2022) · International Conference on Digital Futures and Transformative Technologies (ICoDT2) · doi:10.1109/icodt255437.2022.9787472 · Cited by 8
Learning Disentangled Feature Representations For Anomaly Detection
Lee, W., & Wang, Y.-C. F. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9191201 · Cited by 8
“We follow the leave-one-out setting of [7, 20, 4] in which one class is treated as the anomaly, and the rest of the classes are considered as the normal data.”
MethodGaikwad, B., Patra, A., Crawford, C. R., & Miller, E. L. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109675 · Cited by 7
Yu, Q., Dai, S., Dong, R., & Ikuno, S. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111500 · Cited by 8
Du, M., Gu, S., Qin, Z., Xie, L., Wang, Z., & Hu, Y. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107662 · Cited by 8
Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators
Schulze, J.-P., Sperl, P., & Böttinger, K. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892896 · Cited by 10
Object Class Aware Video Anomaly Detection through Image Translation
Baradaran, M., & Bergevin, R. (2022) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv55824.2022.00020 · Cited by 7
Convolutional autoencoder based on latent subspace projection for anomaly detection
Yu, Q., Li, C., Zhu, Y., & Kurita, T. (2023) · Methods · doi:10.1016/j.ymeth.2023.04.007 · Cited by 7
Anomaly Detection in Aerial Videos Via Future Frame Prediction Networks
Jin, P., Mou, L., Xia, G.-S., & Zhu, X. X. (2021) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss47720.2021.9554396 · Cited by 7
Incremental self-supervised learning based on transformer for anomaly detection and localization
Jin, W., Guo, F., Wu, Q., & Zhu, L. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111978 · Cited by 12
Wu, C., Liu, X., Wu, J., Zhang, H., & Wang, L. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111594 · Cited by 6
Enhancing random surface anomaly detection in real-world using a four-stage one-class approach
Li, P., Wu, G., Zhou, Y., & Leng, J. (2025) · Pattern Recognition Letters · doi:10.1016/j.patrec.2025.05.002 · Cited by 5
“Early approaches typically employed Autoencoders [7] or Generative Adversarial Networks (GANs) [8,9] for image reconstruction.”
A memory-tree driven network for multi-view fusion anomaly detection
Liu, X., Wu, C., Zhang, H., & Wang, L. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112106 · Cited by 5
Deep-Disaster: Unsupervised Disaster Detection and Localization Using Visual Data
Shekarizadeh, S., Rastgoo, R., Al-Kuwari, S. M., & Sabokrou, M. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956722 · Cited by 5
“Each network consists of a generator G and a discriminator D inspired by [31].”
BackgroundMethodFault Diagnosis of Train Clamp Based on Faster R-CNN and One-class Convolutional Neural Network
Zhang, Z., Ma, J., Huang, D., Zhou, Z., Wan, Z., & Qin, N. (2021) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea51954.2021.9516167 · Cited by 5
Bhowmik, N., Gaus, Y. F. A., & Breckon, T. P. (2019) · IEEE Conference on Technologies for Homeland Security (HST) · doi:10.1109/hst47167.2019.9032920 · Cited by 5
“In the works of [12], [24], unsupervised anomaly detection strategies are proposed based on high reconstruction errors produced by a generator network adversarially trained on non-anomalous (benign) stream-of-commerce X-ray imagery only.”
BackgroundSelf-citationFew-Shot Adaptive Detection of Objects of Concern Using Generative Models with Negative Retraining
Dionelis, N., Yaghoobi, M., & Tsaftaris, S. A. (2021) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai52525.2021.00086 · Cited by 5
“The GANomaly and Skip-GANomaly auto-encoders [22], [23] perform OoD detection and are tested on the University Baggage Anomaly (UBA) and Full Firearm Operational Benign (FFOB) datasets.”
MethodImproving novelty detection by self-supervised learning and channel attention mechanism
Tian, M., Cui, Y., Long, H., & Li, J. (2021) · Industrial Robot the international journal of robotics research and application · doi:10.1108/ir-10-2020-0241 · Cited by 4
Zhu, Y., Chen, D., Yang, L., Yuan, G., Wei, R., & Hu, Y. (2021) · Energy Reports · doi:10.1016/j.egyr.2021.01.095 · Cited by 4
Autoencoder-Like Knowledge Distillation Network for Anomaly Detection
Xu, C., Wang, B. J., Ni, D., Gan, J., Wu, M., & Zhou, W. (2023) · IEEE Access · doi:10.1109/access.2023.3314199 · Cited by 4
Coupling of unsupervised and supervised deep learning-based approaches for surface anomaly detection
Rački, D., Tomaževič, D., & Skočaj, D. (2024) · Journal of Electronic Imaging · doi:10.1117/1.jei.33.3.031207 · Cited by 3
“10 Since the introduction of generative adversarial networks (GANs) 11 trained by adversarial loss, generative-based models, such as 12,13 and an improved variation 14,15 based on the mapping from image space to a latent space have been proposed.”
BackgroundMemory association guided unsupervised anomaly detection with adaptive 3D attention
Liu, X., Wu, C., Zhang, H., & Wang, L. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103379 · Cited by 5
Anomaly Detection of Predicted Frames Based on U-Net Feature Vector Reconstruction
Qiang, Y., Fei, S., Jiao, Y., & Li, L. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1627/1/012014 · Cited by 3
“In[5], the author proposes a convolutional neural network structure with an encoder and decoder with jump connections and cites the adversarial training method.”
BackgroundA Weakly-Supervised Anomaly Detection Method via Adversarial Training for Medical Images
Li, H., Iwamoto, Y., Han, X., Lin, L., Tong, R., Hu, H., Furukawa, A., Kanasaki, S., & Chen, Y. (2022) · International Conference on Consumer Electronics · doi:10.1109/icce53296.2022.9730129 · Cited by 3
Xiaopin, 钟. Z., Junwei, 朱. Z., Zhihao, 列. L., & Yuanlong, 邓. D. (2023) · Laser & Optoelectronics Progress · doi:10.3788/lop222111 · Cited by 2
Adversarial Learning Aided Malicious Network Traffic Detection Based on EDE Framework
Zhang, L., Wang, Y., Ohtsuki, T. O., Adebisi, B., Wu, H., & Gui, G. (2023) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc57788.2023.10233524 · Cited by 2
Medical Insurance Medication Anomaly Detection based on Isolated Forest Proximity Matrix
Jiang, X., Lin, K.-B., Zeng, Y., & Yang, F. (2021) · International Conference on Computer Science & Education (ICCSE) · doi:10.1109/iccse51940.2021.9569723 · Cited by 4
Anomaly Detection Based on Deep Learning: Insights and Opportunities
Zhang, H., Xie, R., Li, K., Huang, W., Yang, C., & Liu, J. (2023) · IEEE International Conference on Cyber Security and Cloud Computing / IEEE International Conference on Edge Computing and Scalable Cloud (CSCloud/EdgeCom) · doi:10.1109/cscloud-edgecom58631.2023.00015 · Cited by 2
“Subsequently, a series of improved models appeared for GAN anomaly detection appeared; for example, skipGANomaly has better reconstruction ability and generalization ability [33], DED-GAN has better performance and is suitable for application scenarios with few or difficult to obtain abnormal samples [34], MAD-GAN can…”
BackgroundOne-class Steel Detector Using Patch GAN Discriminator for Visualising Anomalous Feature MapPreprint
Yasuno, T., Fujii, J., & Fukami, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.00143 · Cited by 2
Evaluation of Nested U-Net models performance on MVTec AD dataset
Jonák, M., Ježek, Š., & Bürget, R. (2022) · International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT) · doi:10.1109/icumt57764.2022.9943348 · Cited by 1
“Reconstruction-based methods: These developmentally older methods were originally based on GANs [9] (AnoGAN [11], f-AnoGAN [12], GANomaly [13], SkipGANomaly [14] or DAGAN [15]) and focused on the ability to reconstruct only data without anomalies.”
BackgroundMethodAn Ensemble of Supervised Learning and Image Inpainting for Mura Detection
Lin, C., Chang, T.-M., Chen, H.-Y., & Wei, T.-J. (2023) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew59549.2023.00096 · Cited by 1
“Skip-GANomaly [3] combined the two models of U-Net and GANomaly and used the network structure of skip connection.”
MethodSkip-GANomaly++: Skip Connections and Residual Blocks for Anomaly Detection (Student Abstract)
Park, J., Hong, J.-R., Kim, M.-H., & Kim, T. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i21.30496 · Cited by 1
Research on carotid artery plaque anomaly detection algorithm based on ultrasound images
Li, Y., Li, W., Li, Q., Gao, L., Wang, Y., Li, S., & Wu, B. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109180 · Cited by 1
Mask-patchcore: a robust anomaly detection model focusing on interested region
Wu, F., & Xu, S. (2025) · International Conference on Graphics and Image Processing (ICGIP) · doi:10.1117/12.3057825 · Cited by 1
Integration of Deep Generative Anomaly Detection Algorithm in High-Speed Industrial LinePreprint
Ferrari, N., Zanarini, N., Fraccaroli, M., Bizzarri, A., & Lamma, E. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4858664 · Cited by 1
Li, L., & Ma, A. J. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9534019
“Skip-GANomaly [29] applies skip connection on GANomaly architecture.”
BackgroundImproved Deep Neural Network for Real-Time Detection of Publicly Prohibited ItemsPreprint
Ejiyi, C. J., Ukwuoma, C. C., Nneji, G. U., Monday, H. N., Oluwasanmi, A., Qin, Z., Ejiyi, M. B., & Chikwendu, I. A. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4144996
Cai, X., Xiao, R., Zeng, Z., Gong, P., & Zhang, S. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4191163
Unsupervised anomaly detection based on improved skip-gannomaly
Fan, C. (2022) · International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC) · doi:10.1117/12.2641921
“Later Samet Akçay et al. [13] proposed Skip-GANomaly based on GANomaly, which employs an encoder-decoder convolutional neural network with skip connections to thoroughly capture the multi-scale distribution of the normal data distribution in high-dimensional image space, but accuracy of…”
BackgroundSelf-supervised learning for textured surface anomaly detection and localization
Wang, F., Cheng, F., Zhang, M., & Zhang, H. (2023) · International Conference on Mechatronic Engineering and Artificial Intelligence (MEAI) · doi:10.1117/12.2673155
“On this basis, another model named skip-GANomaly [3] is proposed, where the Autoencoder is a generator used to weight three loss functions to reduce the total loss value and enhance the detection accuracy, and the use of skip-connection in the encoder and decoder improves the reconstruction ability.”
MethodLearning Representations for Novelty and Anomaly Detection
Almohsen, R. (2023) · doi:10.33915/etd.11639
“are based on learning a close approximation to the true distribution of normal instances by using generative methods, such as [4, 6].”
MethodWang, X., & Li, W. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4511134
Image Inpainting with Self-Supervised Learning for Mura Detection System
Chang, T.-M., Chen, H.-Y., & Lin, C. (2023) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan58799.2023.10227069
Liu, M., Jiao, Y., Lü, J., & Chen, H. (2023) · doi:10.36227/techrxiv.24330880
Mtddpm: Visual Anomaly Detection with Multiscale Denoising Diffusion Probabilistic ModelPreprint
Wang, X., & Li, W. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4632278
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
