{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T17:24:19Z","timestamp":1754155459731,"version":"3.41.2"},"reference-count":32,"publisher":"Emerald","issue":"5","license":[{"start":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T00:00:00Z","timestamp":1622764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IR"],"published-print":{"date-parts":[[2021,9,21]]},"abstract":"<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title>\n<jats:p>In novelty detection, the autoencoder based image reconstruction strategy is one of the mainstream solutions. The basic idea is that once the autoencoder is trained on normal data, it has a low reconstruction error on normal data. However, when faced with complex natural images, the conventional pixel-level reconstruction becomes poor and does not show the promising results. This paper aims to provide a new method for improving the performance of novelty detection based autoencoder.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title>\n<jats:p>To solve the problem that conventional pixel-level reconstruction cannot effectively extract the global semantic information of the image, a novel model with the combination of attention mechanism and self-supervised learning method is proposed. First, an auxiliary task, reconstruct rotated image, is set to enable the network to learn global semantic feature information. Then, the channel attention mechanism is introduced to perform adaptive feature refinement on the intermediate feature map to optimize the correspondingly passed feature map.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Findings<\/jats:title>\n<jats:p>Experimental results on three public data sets show that the proposed method has potential performance for novelty detection.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title>\n<jats:p>This study explores the ability of self-supervised learning methods and attention mechanism to extract features on a single class of images. In this way, the performance of novelty detection can be improved.<\/jats:p>\n<\/jats:sec>","DOI":"10.1108\/ir-10-2020-0241","type":"journal-article","created":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T13:47:55Z","timestamp":1622814475000},"page":"673-679","source":"Crossref","is-referenced-by-count":3,"title":["Improving novelty detection by self-supervised learning and channel attention mechanism"],"prefix":"10.1108","volume":"48","author":[{"given":"Miao","family":"Tian","sequence":"first","affiliation":[]},{"given":"Ying","family":"Cui","sequence":"additional","affiliation":[]},{"given":"Haixia","family":"Long","sequence":"additional","affiliation":[]},{"given":"Junxia","family":"Li","sequence":"additional","affiliation":[]}],"member":"140","published-online":{"date-parts":[[2021,6,4]]},"reference":[{"year":"2019","first-page":"481","article-title":"Latent space autoregression for novelty detection","key":"key2021091915523918300_ref001"},{"key":"key2021091915523918300_ref002","first-page":"622","article-title":"Ganomaly: semi-supervised anomaly detection via adversarial training","volume-title":"Asian conference on computer vision","year":"2018"},{"key":"key2021091915523918300_ref003","first-page":"1","article-title":"Skip-ganomaly: skip connected and adversarially trained encoder-decoder anomaly detection","volume-title":"2019 International Joint Conference on Neural Networks (IJCNN)","year":"2019"},{"volume-title":"Pattern Recognition and Machine Learning","year":"2006","key":"key2021091915523918300_ref004"},{"key":"key2021091915523918300_ref005","first-page":"34","article-title":"One-class SVM for learning in image retrieval","volume-title":"Proceedings 2001 International Conference on Image Processing (Cat. No. 01CH37205)","year":"2001"},{"volume-title":"International Conference on Learning Representations (ICLR).","year":"2018","article-title":"Unsupervised representation learning by predicting image rotations","key":"key2021091915523918300_ref006"},{"issue":"1\/3","key":"key2021091915523918300_ref007","article-title":"Computer vision for autonomous vehicles: problems, datasets and state of the art","volume":"12","year":"2017","journal-title":"Foundations and Trends\u00ae in Computer Graphics and Vision"},{"volume-title":"International Conference on Learning Representations (ICLR).","year":"2013","article-title":"Auto-encoding variational Bayes","key":"key2021091915523918300_ref008"},{"key":"key2021091915523918300_ref009","first-page":"1920","article-title":"Revisiting self-supervised visual representation learning","volume-title":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition","year":"2019"},{"year":"2009","article-title":"Learning multiple layers of features from tiny images","key":"key2021091915523918300_ref010"},{"year":"2010","article-title":"Cifar-10 (Canadian institute for advanced research)","key":"key2021091915523918300_ref011"},{"year":"2018","article-title":"Anomaly detection with generative adversarial networks for multivariate time series","key":"key2021091915523918300_ref012"},{"key":"key2021091915523918300_ref013","first-page":"6536","article-title":"Future frame prediction for anomaly detection \u2013 a new baseline","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","year":"2018"},{"year":"1996","article-title":"Columbia Object image library (coil-100)","key":"key2021091915523918300_ref014"},{"key":"key2021091915523918300_ref015","first-page":"1","article-title":"Active authentication using an autoencoder regularized cnn-based one-class classifier","volume-title":"2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)","year":"2019"},{"year":"2019","first-page":"2898","article-title":"Ocgan: one-class novelty detection using gans with constrained latent representations","key":"key2021091915523918300_ref016"},{"key":"key2021091915523918300_ref017","first-page":"6822","article-title":"Generative probabilistic novelty detection with adversarial autoencoders","volume-title":"Advances in Neural Information Processing Systems","year":"2018"},{"year":"2015","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","key":"key2021091915523918300_ref018"},{"key":"key2021091915523918300_ref019","first-page":"124","article-title":"Novelty detection using extreme value statistics","volume-title":"IEE Proceedings-Vision, Image and Signal Processing","year":"1999"},{"key":"key2021091915523918300_ref020","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","year":"2015"},{"key":"key2021091915523918300_ref021","first-page":"4393","article-title":"Deep one-class classification","volume-title":"International conference on machine learning","year":"2018"},{"year":"2018","first-page":"3379","article-title":"Adversarially learned one-class classifier for novelty detection","key":"key2021091915523918300_ref022"},{"key":"key2021091915523918300_ref023","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1145\/2689746.2689747","article-title":"Anomaly detection using autoencoders with nonlinear dimensionality reduction","volume-title":"Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis","year":"2014"},{"key":"key2021091915523918300_ref024","first-page":"146","article-title":"Unsupervised anomaly detection with generative adversarial networks to guide marker discovery","volume-title":"International conference on information processing in medical imaging","year":"2017"},{"key":"key2021091915523918300_ref025","first-page":"4790","article-title":"Conditional image generation with pixelcnn decoders","volume-title":"Advances in Neural Information Processing Systems","year":"2016"},{"key":"key2021091915523918300_ref026","first-page":"3156","article-title":"Residual attention network for image classification","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","year":"2017"},{"year":"2018","first-page":"3","article-title":"Cbam: convolutional block attention module","key":"key2021091915523918300_ref027"},{"year":"2018","article-title":"Efficient gan-based anomaly detection","key":"key2021091915523918300_ref028"},{"key":"key2021091915523918300_ref029","first-page":"1100","article-title":"Deep structured energy based models for anomaly detection","volume-title":"International Conference on Machine Learning","year":"2016"},{"year":"2018","first-page":"9673","article-title":"Intelligent collaborative localization among air-ground robots for industrial environment perception","key":"key2021091915523918300_ref030"},{"issue":"11","key":"key2021091915523918300_ref031","doi-asserted-by":"crossref","first-page":"3052","DOI":"10.1109\/TVCG.2019.2932216","article-title":"Hierarchical topic model based object association for semantic SLAM","volume":"25","year":"2019","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"volume-title":"International Conference on Learning Representations","year":"2018","article-title":"Deep autoencoding gaussian mixture model for unsupervised anomaly detection","key":"key2021091915523918300_ref032"}],"container-title":["Industrial Robot: the international journal of robotics research and application"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IR-10-2020-0241\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IR-10-2020-0241\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T21:40:12Z","timestamp":1753393212000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/ir\/article\/48\/5\/673-679\/176412"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,4]]},"references-count":32,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2021,6,4]]},"published-print":{"date-parts":[[2021,9,21]]}},"alternative-id":["10.1108\/IR-10-2020-0241"],"URL":"https:\/\/doi.org\/10.1108\/ir-10-2020-0241","relation":{},"ISSN":["0143-991X","0143-991X"],"issn-type":[{"type":"print","value":"0143-991X"},{"type":"print","value":"0143-991X"}],"subject":[],"published":{"date-parts":[[2021,6,4]]}}}