{"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-requires-better","title":"Anomaly Detection Requires Better Representations","arxiv_id":"2210.10773","date":"2022-10-19","proceeding":null,"authors":["Tal Reiss","Niv Cohen","Eliahu Horwitz","Ron Abutbul","Yedid Hoshen"],"abstract":"Anomaly detection seeks to identify unusual phenomena, a central task in science and industry. The task is inherently unsupervised as anomalies are unexpected and unknown during training. Recent advances in self-supervised representation learning have directly driven improvements in anomaly detection. In this position paper, we first explain how self-supervised representations can be easily used to achieve state-of-the-art performance in commonly reported anomaly detection benchmarks. We then argue that tackling the next generation of anomaly detection tasks requires new technical and conceptual improvements in representation learning.","url_abs":"https://arxiv.org/abs/2210.10773v1","url_pdf":"https://arxiv.org/pdf/2210.10773v1.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-requires-better","repo_url":"https://github.com/eliahuhorwitz/3D-ADS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-anomaly-detection-and-segmentation","task_name":"3D Anomaly Detection and Segmentation"},{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":null,"task_name":"Position"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/anomaly-detection-on-odds","task":"Anomaly Detection","dataset":"ODDS","model":"kNN","rank_in_archive_order":1,"of":3,"metrics":{"AUROC":"0.902","F1":"0.699"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-odds","task":"Anomaly Detection","dataset":"ODDS","model":"ICL","rank_in_archive_order":2,"of":3,"metrics":{"AUROC":"0.889","F1":"0.681"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-odds","task":"Anomaly Detection","dataset":"ODDS","model":"GOAD","rank_in_archive_order":3,"of":3,"metrics":{"AUROC":"0.782","F1":"0.544"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-one-class-cifar-10","task":"Anomaly Detection","dataset":"One-class CIFAR-10","model":"DINO-FT","rank_in_archive_order":8,"of":36,"metrics":{"AUROC":"98.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.10773","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}