{"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/are-generative-deep-models-for-novelty","title":"Are generative deep models for novelty detection truly better?","arxiv_id":"1807.05027","date":"2018-07-13","proceeding":null,"authors":["Vít Škvára","Tomáš Pevný","Václav Šmídl"],"abstract":"Many deep models have been recently proposed for anomaly detection. This\npaper presents comparison of selected generative deep models and classical\nanomaly detection methods on an extensive number of non--image benchmark\ndatasets. We provide statistical comparison of the selected models, in many\nconfigurations, architectures and hyperparamaters. We arrive to conclusion that\nperformance of the generative models is determined by the process of selection\nof their hyperparameters. Specifically, performance of the deep generative\nmodels deteriorates with decreasing amount of anomalous samples used in\nhyperparameter selection. In practical scenarios of anomaly detection, none of\nthe deep generative models systematically outperforms the kNN.","url_abs":"http://arxiv.org/abs/1807.05027v1","url_pdf":"http://arxiv.org/pdf/1807.05027v1.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":"are-generative-deep-models-for-novelty","repo_url":"https://github.com/smidl/AnomalyDetection.jl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"novelty-detection","task_name":"Novelty Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.05027","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}