{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/adversarially-learned-one-class-classifier","title":"Adversarially Learned One-Class Classifier for Novelty Detection","arxiv_id":"1802.09088","date":"2018-02-25","proceeding":"CVPR 2018 6","authors":["Mohammad Sabokrou","Mohammad Khalooei","Mahmood Fathy","Ehsan Adeli"],"abstract":"Novelty detection is the process of identifying the observation(s) that\ndiffer in some respect from the training observations (the target class). In\nreality, the novelty class is often absent during training, poorly sampled or\nnot well defined. Therefore, one-class classifiers can efficiently model such\nproblems. However, due to the unavailability of data from the novelty class,\ntraining an end-to-end deep network is a cumbersome task. In this paper,\ninspired by the success of generative adversarial networks for training deep\nmodels in unsupervised and semi-supervised settings, we propose an end-to-end\narchitecture for one-class classification. Our architecture is composed of two\ndeep networks, each of which trained by competing with each other while\ncollaborating to understand the underlying concept in the target class, and\nthen classify the testing samples. One network works as the novelty detector,\nwhile the other supports it by enhancing the inlier samples and distorting the\noutliers. The intuition is that the separability of the enhanced inliers and\ndistorted outliers is much better than deciding on the original samples. The\nproposed framework applies to different related applications of anomaly and\noutlier detection in images and videos. The results on MNIST and Caltech-256\nimage datasets, along with the challenging UCSD Ped2 dataset for video anomaly\ndetection illustrate that our proposed method learns the target class\neffectively and is superior to the baseline and state-of-the-art methods.","url_abs":"http://arxiv.org/abs/1802.09088v2","url_pdf":"http://arxiv.org/pdf/1802.09088v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"adversarially-learned-one-class-classifier","repo_url":"https://github.com/khalooei/ALOCC-CVPR2018","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adversarially-learned-one-class-classifier","repo_url":"https://github.com/Ars235/Novelty_Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"adversarially-learned-one-class-classifier","repo_url":"https://github.com/ErikKratzCth/ALOCC_Keras_SMILE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"adversarially-learned-one-class-classifier","repo_url":"https://github.com/Tony607/ALOCC_Keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"adversarially-learned-one-class-classifier","repo_url":"https://github.com/kzkadc/alocc_mnist","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"novelty-detection","task_name":"Novelty Detection"},{"task_slug":"one-class-classification","task_name":"One-Class Classification"},{"task_slug":"one-class-classifier","task_name":"One-class classifier"},{"task_slug":"outlier-detection","task_name":"Outlier Detection"},{"task_slug":"video-anomaly-detection","task_name":"Video Anomaly Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.09088","atlas_url":"https://app.syntology.ai/?focus=1802.09088","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}