{"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/center-aware-residual-anomaly-synthesis-for","title":"Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection","arxiv_id":"2505.17551","date":"2025-05-23","proceeding":null,"authors":["Qiyu Chen","Huiyuan Luo","Haiming Yao","Wei Luo","Zhen Qu","Chengkan Lv","Zhengtao Zhang"],"abstract":"Anomaly detection plays a vital role in the inspection of industrial images. Most existing methods require separate models for each category, resulting in multiplied deployment costs. This highlights the challenge of developing a unified model for multi-class anomaly detection. However, the significant increase in inter-class interference leads to severe missed detections. Furthermore, the intra-class overlap between normal and abnormal samples, particularly in synthesis-based methods, cannot be ignored and may lead to over-detection. To tackle these issues, we propose a novel Center-aware Residual Anomaly Synthesis (CRAS) method for multi-class anomaly detection. CRAS leverages center-aware residual learning to couple samples from different categories into a unified center, mitigating the effects of inter-class interference. To further reduce intra-class overlap, CRAS introduces distance-guided anomaly synthesis that adaptively adjusts noise variance based on normal data distribution. Experimental results on diverse datasets and real-world industrial applications demonstrate the superior detection accuracy and competitive inference speed of CRAS. The source code and the newly constructed dataset are publicly available at https://github.com/cqylunlun/CRAS.","url_abs":"https://arxiv.org/abs/2505.17551v1","url_pdf":"https://arxiv.org/pdf/2505.17551v1.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":"center-aware-residual-anomaly-synthesis-for","repo_url":"https://github.com/cqylunlun/CRAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"multi-class-anomaly-detection","task_name":"Multi-class Anomaly Detection"}],"methods":[],"datasets_introduced":[{"slug":"itdd","name":"ITDD","full_name":"Industrial Textile Defect Detection"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/anomaly-detection-on-itdd","task":"Anomaly Detection","dataset":"ITDD","model":"CRAS","rank_in_archive_order":1,"of":1,"metrics":{"Detection AUROC":"99.6","Segmentation AUROC":"98.0"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-mpdd","task":"Anomaly Detection","dataset":"MPDD","model":"CRAS","rank_in_archive_order":2,"of":16,"metrics":{"Detection AUROC":"98.8","Segmentation AUROC":"98.7"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-mvtec-ad","task":"Anomaly Detection","dataset":"MVTec AD","model":"CRAS","rank_in_archive_order":15,"of":148,"metrics":{"Detection AUROC":"99.7","Segmentation AUROC":"98.4"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-visa","task":"Anomaly Detection","dataset":"VisA","model":"CRAS","rank_in_archive_order":18,"of":50,"metrics":{"Detection AUROC":"97.0","Segmentation AUROC":"98.4"},"uses_additional_data":false},{"leaderboard":"/sota/multi-class-anomaly-detection-on-itdd","task":"Multi-class Anomaly Detection","dataset":"ITDD","model":"CRAS","rank_in_archive_order":1,"of":1,"metrics":{"Detection AUROC":"99.4","Segmentation AUROC":"97.8"},"uses_additional_data":false},{"leaderboard":"/sota/multi-class-anomaly-detection-on-mvtec-ad","task":"Multi-class Anomaly Detection","dataset":"MVTec AD","model":"CRAS","rank_in_archive_order":9,"of":13,"metrics":{"Detection AUROC":"98.3","Segmentation AUROC":"98.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.17551","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}