{"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/domain-independent-detection-of-known","title":"Domain-independent detection of known anomalies","arxiv_id":"2407.02910","date":"2024-07-03","proceeding":null,"authors":["Jonas Bühler","Jonas Fehrenbach","Lucas Steinmann","Christian Nauck","Marios Koulakis"],"abstract":"One persistent obstacle in industrial quality inspection is the detection of anomalies. In real-world use cases, two problems must be addressed: anomalous data is sparse and the same types of anomalies need to be detected on previously unseen objects. Current anomaly detection approaches can be trained with sparse nominal data, whereas domain generalization approaches enable detecting objects in previously unseen domains. Utilizing those two observations, we introduce the hybrid task of domain generalization on sparse classes. To introduce an accompanying dataset for this task, we present a modification of the well-established MVTec AD dataset by generating three new datasets. In addition to applying existing methods for benchmark, we design two embedding-based approaches, Spatial Embedding MLP (SEMLP) and Labeled PatchCore. Overall, SEMLP achieves the best performance with an average image-level AUROC of 87.2 % vs. 80.4 % by MIRO. The new and openly available datasets allow for further research to improve industrial anomaly detection.","url_abs":"https://arxiv.org/abs/2407.02910v1","url_pdf":"https://arxiv.org/pdf/2407.02910v1.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":"domain-independent-detection-of-known","repo_url":"https://github.com/Jonas1302/anomalib","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"}],"methods":[],"datasets_introduced":[{"slug":"domain-independent-anomalies-datasets","name":"Domain-independent anomalies datasets","full_name":"Domain-independent anomalies datasets (adaptions of the MVTec Anomaly Detection dataset)"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/on-domain-independent-anomalies-datasets","task":"","dataset":"Domain-independent anomalies datasets","model":"Spatial Embedding MLP (ViT-B/8)","rank_in_archive_order":1,"of":2,"metrics":{"Detection AUROC":"86.7","F1-score":"85"},"uses_additional_data":false},{"leaderboard":"/sota/on-domain-independent-anomalies-datasets","task":"","dataset":"Domain-independent anomalies datasets","model":"Spatial Embedding MLP (Wide-ResNet50-2)","rank_in_archive_order":2,"of":2,"metrics":{"Detection AUROC":"87.2","F1-score":"84.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}