{"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/anomaly-detection-with-adversarial-dual","title":"Anomaly Detection with Adversarial Dual Autoencoders","arxiv_id":"1902.06924","date":"2019-02-19","proceeding":"arXiv.org 2019 2","authors":["Ha Son Vu","Daisuke Ueta","Kiyoshi Hashimoto","Kazuki Maeno","Sugiri Pranata","Sheng Mei Shen"],"abstract":"Semi-supervised and unsupervised Generative Adversarial Networks (GAN)-based\nmethods have been gaining popularity in anomaly detection task recently.\nHowever, GAN training is somewhat challenging and unstable. Inspired from\nprevious work in GAN-based image generation, we introduce a GAN-based anomaly\ndetection framework - Adversarial Dual Autoencoders (ADAE) - consists of two\nautoencoders as generator and discriminator to increase training stability. We\nalso employ discriminator reconstruction error as anomaly score for better\ndetection performance. Experiments across different datasets of varying\ncomplexity show strong evidence of a robust model that can be used in different\nscenarios, one of which is brain tumor detection.","url_abs":"http://arxiv.org/abs/1902.06924v1","url_pdf":"http://arxiv.org/pdf/1902.06924v1.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":"anomaly-detection-with-adversarial-dual","repo_url":"https://github.com/YeongHyeon/ADAE-TF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"anomaly-detection-with-adversarial-dual","repo_url":"https://github.com/kjm1559/ADAE_LSTM_Autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"anomaly-detection-with-adversarial-dual","repo_url":"https://github.com/shijianjian/Adverserial-Dual-AutoEncoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.06924","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}