{"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/pyramidflow-high-resolution-defect","title":"PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow","arxiv_id":"2303.02595","date":"2023-03-05","proceeding":"CVPR 2023 1","authors":["Jiarui Lei","Xiaobo Hu","Yue Wang","Dong Liu"],"abstract":"During industrial processing, unforeseen defects may arise in products due to uncontrollable factors. Although unsupervised methods have been successful in defect localization, the usual use of pre-trained models results in low-resolution outputs, which damages visual performance. To address this issue, we propose PyramidFlow, the first fully normalizing flow method without pre-trained models that enables high-resolution defect localization. Specifically, we propose a latent template-based defect contrastive localization paradigm to reduce intra-class variance, as the pre-trained models do. In addition, PyramidFlow utilizes pyramid-like normalizing flows for multi-scale fusing and volume normalization to help generalization. Our comprehensive studies on MVTecAD demonstrate the proposed method outperforms the comparable algorithms that do not use external priors, even achieving state-of-the-art performance in more challenging BTAD scenarios.","url_abs":"https://arxiv.org/abs/2303.02595v1","url_pdf":"https://arxiv.org/pdf/2303.02595v1.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":[],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[{"method_slug":"normalizing-flows","method_name":"Normalizing Flows"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/anomaly-detection-on-btad","task":"Anomaly Detection","dataset":"BTAD","model":"PyramidFlow (Res18)","rank_in_archive_order":5,"of":15,"metrics":{"Detection AUROC":"95.8","Segmentation AUROC":"97.7"},"uses_additional_data":true},{"leaderboard":"/sota/anomaly-detection-on-mvtec-ad","task":"Anomaly Detection","dataset":"MVTec AD","model":"PyramidFlow (Res18)","rank_in_archive_order":125,"of":148,"metrics":{"Segmentation AUPRO":"96.5","Segmentation AUROC":"97.1"},"uses_additional_data":false},{"leaderboard":"/sota/anomaly-detection-on-mvtec-ad","task":"Anomaly Detection","dataset":"MVTec AD","model":"PyramidFlow (FNF)","rank_in_archive_order":127,"of":148,"metrics":{"Segmentation AUPRO":"94.5","Segmentation AUROC":"96.0"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2303.02595","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}