{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:30:12Z","timestamp":1768782612249,"version":"3.49.0"},"reference-count":51,"publisher":"Institution of Engineering and Technology (IET)","issue":"8","license":[{"start":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T00:00:00Z","timestamp":1719273600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Computer Vision"],"published-print":{"date-parts":[[2024,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Anomaly Detection, also known as outlier detection, is critical in domains such as network security, intrusion detection, and fraud detection. One popular approach to anomaly detection is using autoencoders, which are trained to reconstruct input by minimising reconstruction error with the neural network. However, these methods usually suffer from the trade\u2010off between normal reconstruction fidelity and abnormal reconstruction distinguishability, which damages the performance. The authors find that the above trade\u2010off can be better mitigated by imposing constraints on the latent space of images. To this end, the authors propose a new Dual Adversarial Network (DualAD) that consists of a Feature Constraint (FC) module and a reconstruction module. The method incorporates the FC module during the reconstruction training process to impose constraints on the latent space of images, thereby yielding feature representations more conducive to anomaly detection. Additionally, the authors employ dual adversarial learning to model the distribution of normal data. On the one hand, adversarial learning was implemented during the reconstruction process to obtain higher\u2010quality reconstruction samples, thereby preventing the effects of blurred image reconstructions on model performance. On the other hand, the authors utilise adversarial training of the FC module and the reconstruction module to achieve superior feature representation, making anomalies more distinguishable at the feature level. During the inference phase, the authors perform anomaly detection simultaneously in the pixel and latent spaces to identify abnormal patterns more comprehensively. Experiments on three data sets CIFAR10, MNIST, and FashionMNIST demonstrate the validity of the authors\u2019 work. Results show that constraints on the latent space and adversarial learning can improve detection performance.<\/jats:p>","DOI":"10.1049\/cvi2.12297","type":"journal-article","created":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T01:13:33Z","timestamp":1719364413000},"page":"1138-1148","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DualAD: Dual adversarial network for image anomaly detection\u22c6"],"prefix":"10.1049","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3389-5190","authenticated-orcid":false,"given":"Yonghao","family":"Wan","sequence":"first","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics  Nanjing China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3949-1883","authenticated-orcid":false,"given":"Aimin","family":"Feng","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics  Nanjing China"}]}],"member":"265","published-online":{"date-parts":[[2024,6,25]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"e_1_2_10_3_1","doi-asserted-by":"crossref","first-page":"1777","DOI":"10.1145\/3319535.3363224","volume-title":"Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security","author":"Liu F.","year":"2019"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/tnet.2021.3137084"},{"key":"e_1_2_10_5_1","article-title":"Credit card fraud detection in e\u2010commerce: an outlier detection approach","author":"Porwal U.","year":"2018","journal-title":"arXiv: Learning,arXiv: Learning"},{"key":"e_1_2_10_6_1","volume-title":"International Conference on Learning Representations,International Conference on Learning Representations","author":"Zong B.","year":"2018"},{"key":"e_1_2_10_7_1","volume-title":"2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition \u2010 Volume 2 (CVPR\u201906)","author":"Hadsell R.","year":"2006"},{"key":"e_1_2_10_8_1","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow I.","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_2_10_9_1","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Perera P.","year":"2019"},{"key":"e_1_2_10_10_1","doi-asserted-by":"crossref","unstructured":"Schlegl T. et\u00a0al.:Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery pp.146\u2013157(2017).https:\/\/doi.org\/10.1007\/978\u20103\u2010319\u201059050\u20109_12","DOI":"10.1007\/978-3-319-59050-9_12"},{"key":"e_1_2_10_11_1","volume-title":"2018 IEEE International Conference on Data Mining (ICDM)","author":"Zenati H.","year":"2018"},{"key":"e_1_2_10_12_1","doi-asserted-by":"crossref","unstructured":"Akcay S. Atapour\u2010Abarghouei A. Breckon T.P.:GANomaly: Semi\u2010supervised Anomaly Detection via Adversarial Training pp.622\u2013637(2019).https:\/\/doi.org\/10.1007\/978\u20103\u2010030\u201020893\u20106_39","DOI":"10.1007\/978-3-030-20893-6_39"},{"key":"e_1_2_10_13_1","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zaigham Zaheer M.","year":"2020"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976601750264965"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"e_1_2_10_16_1","first-page":"4393","volume-title":"International Conference on Machine Learning","author":"Ruff L.","year":"2018"},{"key":"e_1_2_10_17_1","article-title":"Adversarial autoencoders","author":"Makhzani A.","year":"2015","journal-title":"arXiv preprint arXiv:1511.05644"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3439950"},{"key":"e_1_2_10_19_1","doi-asserted-by":"crossref","unstructured":"Yi J. Yoon S.:Patch SVDD: Patch\u2010Level SVDD for Anomaly Detection and Segmentation pp.375\u2013390(2021).https:\/\/doi.org\/10.1007\/978\u20103\u2010030\u201069544\u20106_23","DOI":"10.1007\/978-3-030-69544-6_23"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.04.020"},{"key":"e_1_2_10_21_1","volume-title":"2021 IEEE International Conference on Multimedia and Expo (ICME)","author":"Hu C.","year":"2021"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3130074"},{"key":"e_1_2_10_23_1","volume-title":"2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC)","author":"Sauter D.","year":"2021"},{"key":"e_1_2_10_24_1","volume-title":"Dasvdd: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection","author":"Hojjati H.","year":"2021"},{"key":"e_1_2_10_25_1","volume-title":"Explainable Deep One\u2010Class Classification","author":"Liznerski P.","year":"2020"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1049\/cvi2.12082"},{"key":"e_1_2_10_27_1","volume-title":"Learning and Evaluating Representations for Deep One\u2010Class Classification","author":"Sohn K.","year":"2020"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.089"},{"key":"e_1_2_10_29_1","first-page":"383","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Chen Y.","year":"2022"},{"key":"e_1_2_10_30_1","volume-title":"2022 IEEE\/ACIS 7th International Conference on Big Data, Cloud Computing, and Data Science (BCD)","author":"Gia T.L.","year":"2022"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0167\u20108655(00)00131\u20108"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0167\u20108655(03)00003\u20105"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3068335"},{"key":"e_1_2_10_34_1","volume-title":"2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","author":"Artola A.","year":"2023"},{"key":"e_1_2_10_35_1","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Yang X.","year":"2019"},{"key":"e_1_2_10_36_1","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Sabokrou M.","year":"2001"},{"key":"e_1_2_10_37_1","article-title":"Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion","author":"Vincent P.","year":"2010","journal-title":"Journal of Machine Learning Research,Journal of Machine Learning Research"},{"key":"e_1_2_10_38_1","article-title":"Fence gan: towards better anomaly detection","author":"Ngo C.","year":"2019","journal-title":"arXiv: Learning,arXiv: Learning"},{"key":"e_1_2_10_39_1","first-page":"20402","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Liu Z.","year":"2023"},{"key":"e_1_2_10_40_1","volume-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Gong D.","year":"2019"},{"key":"e_1_2_10_41_1","article-title":"Auto\u2010encoding variational bayes","author":"Kingma D.","year":"2013","journal-title":"arXiv: Mach. Learn."},{"key":"e_1_2_10_42_1","volume-title":"International Conference on Computer Vision,International Conference on Computer Vision","author":"Zavrtanik V.","year":"2021"},{"key":"e_1_2_10_43_1","unstructured":"Xing P. Sun Y. Li Z.:Self\u2010supervised Guided Segmentation Framework for Unsupervised Anomaly Detection(2022)"},{"key":"e_1_2_10_44_1","unstructured":"Zavrtanik V. Kristan M. Sko\u010daj D.:Dsr \u2010a dual subspace re\u2010projection network for surface anomaly detection"},{"key":"e_1_2_10_45_1","doi-asserted-by":"crossref","unstructured":"Schl\u00fcter H. et\u00a0al.:Natural Synthetic Anomalies for Self\u2010Supervised Anomaly Detection and Localization(2021)","DOI":"10.1007\/978-3-031-19821-2_27"},{"key":"e_1_2_10_46_1","unstructured":"Bauer A.:Self\u2010supervised Training with Autoencoders for Visual Anomaly Detection(2022)"},{"key":"e_1_2_10_47_1","volume-title":"Improved Techniques for Training Gans","author":"Salimans T.","year":"2016"},{"key":"e_1_2_10_48_1","article-title":"Adam: a method for stochastic optimization","author":"Kingma D.","year":"2014","journal-title":"arXiv: Learning,arXiv: Learning"},{"key":"e_1_2_10_49_1","volume-title":"Conference on Learning Theory,Conference on Learning Theory","author":"Duchi J.","year":"2010"},{"key":"e_1_2_10_50_1","unstructured":"LeCun Y.:The mnist database of handwritten digits.http:\/\/yann.lecun.com\/exdb\/mnist\/(1998)"},{"key":"e_1_2_10_51_1","article-title":"Fashion\u2010mnist: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao H.","year":"2017","journal-title":"arXiv: Learning,arXiv: Learning"},{"key":"e_1_2_10_52_1","unstructured":"Krizhevsky A.:Learning Multiple Layers of Features from Tiny Images(2009)"}],"container-title":["IET Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cvi2.12297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T11:37:03Z","timestamp":1761565023000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cvi2.12297"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,25]]},"references-count":51,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["10.1049\/cvi2.12297"],"URL":"https:\/\/doi.org\/10.1049\/cvi2.12297","archive":["Portico"],"relation":{},"ISSN":["1751-9632","1751-9640"],"issn-type":[{"value":"1751-9632","type":"print"},{"value":"1751-9640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,25]]},"assertion":[{"value":"2024-01-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}