{"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/dsr-a-dual-subspace-re-projection-network-for","title":"DSR -- A dual subspace re-projection network for surface anomaly detection","arxiv_id":"2208.01521","date":"2022-08-02","proceeding":null,"authors":["Vitjan Zavrtanik","Matej Kristan","Danijel Skočaj"],"abstract":"The state-of-the-art in discriminative unsupervised surface anomaly detection relies on external datasets for synthesizing anomaly-augmented training images. Such approaches are prone to failure on near-in-distribution anomalies since these are difficult to be synthesized realistically due to their similarity to anomaly-free regions. We propose an architecture based on quantized feature space representation with dual decoders, DSR, that avoids the image-level anomaly synthesis requirement. Without making any assumptions about the visual properties of anomalies, DSR generates the anomalies at the feature level by sampling the learned quantized feature space, which allows a controlled generation of near-in-distribution anomalies. DSR achieves state-of-the-art results on the KSDD2 and MVTec anomaly detection datasets. The experiments on the challenging real-world KSDD2 dataset show that DSR significantly outperforms other unsupervised surface anomaly detection methods, improving the previous top-performing methods by 10% AP in anomaly detection and 35% AP in anomaly localization.","url_abs":"https://arxiv.org/abs/2208.01521v2","url_pdf":"https://arxiv.org/pdf/2208.01521v2.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":"dsr-a-dual-subspace-re-projection-network-for","repo_url":"https://github.com/vitjanz/dsr_anomaly_detection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"anomaly-localization","task_name":"Anomaly Localization"},{"task_slug":"defect-detection","task_name":"Defect Detection"},{"task_slug":"supervised-defect-detection","task_name":"Supervised Defect Detection"},{"task_slug":"unsupervised-anomaly-detection","task_name":"Unsupervised Anomaly Detection"},{"task_slug":"weakly-supervised-defect-detection","task_name":"Weakly Supervised Defect Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/anomaly-detection-on-mvtec-ad","task":"Anomaly Detection","dataset":"MVTec AD","model":"DSR","rank_in_archive_order":65,"of":148,"metrics":{"Detection AUROC":"98.2","Segmentation AP":"70.2"},"uses_additional_data":true},{"leaderboard":"/sota/anomaly-detection-on-mvtec-loco-ad","task":"Anomaly Detection","dataset":"MVTec LOCO AD","model":"DSR","rank_in_archive_order":24,"of":40,"metrics":{"Avg. Detection AUROC":"82.6","Detection AUROC (only logical)":"75.0","Detection AUROC (only structural)":"90.2","Segmentation AU-sPRO (until FPR 5%)":"58.5"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-visa","task":"Anomaly Detection","dataset":"VisA","model":"DSR","rank_in_archive_order":46,"of":50,"metrics":{"Segmentation AUPRO (until 30% FPR)":"68.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-anomaly-detection-on","task":"Unsupervised Anomaly Detection","dataset":"KolektorSDD2","model":"DSR","rank_in_archive_order":2,"of":3,"metrics":{"Detection AP":"87.2","Segmentation AP":"61.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.01521","atlas_url":"https://app.syntology.ai/?focus=2208.01521","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}