{"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/rapp-novelty-detection-with-reconstruction","title":"RaPP: Novelty Detection with Reconstruction along Projection Pathway","arxiv_id":null,"date":"2020-05-01","proceeding":"ICLR 2020 1","authors":["Ki Hyun Kim","Sangwoo Shim","Yongsub Lim","Jongseob Jeon","Jeongwoo Choi","Byungchan Kim","Andre S. Yoon"],"abstract":"We propose RaPP, a new methodology for novelty detection by utilizing hidden space activation values obtained from a deep autoencoder.\nPrecisely, RaPP compares input and its autoencoder reconstruction not only in the input space but also in the hidden spaces.\nWe show that if we feed a reconstructed input to the same autoencoder again, its activated values in a hidden space are equivalent to the corresponding reconstruction in that hidden space given the original input.\nIn order to aggregate the hidden space activation values, we propose two metrics, which enhance the novelty detection performance.\nThrough extensive experiments using diverse datasets, we validate that RaPP improves novelty detection performances of autoencoder-based approaches.\nBesides, we show that RaPP outperforms recent novelty detection methods evaluated on popular benchmarks.\n","url_abs":"https://openreview.net/forum?id=HkgeGeBYDB","url_pdf":"https://openreview.net/pdf?id=HkgeGeBYDB","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":"rapp-novelty-detection-with-reconstruction","repo_url":"https://github.com/Aiden-Jeon/RaPP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"novelty-detection","task_name":"Novelty Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}