{"url":"/sota/anomaly-detection-on-mpdd","task":{"name":"Anomaly Detection","url":"/task/anomaly-detection","note":null},"dataset":{"name":"MPDD","url":"/dataset/mpdd"},"category":"Computer Vision","categories":["Computer Vision","Graphs","Methodology","Miscellaneous"],"category_note":null,"description":"**Anomaly Detection** is a binary classification identifying unusual or unexpected patterns in a dataset, which deviate significantly from the majority of the data. The goal of anomaly detection is to identify such anomalies, which could represent errors, fraud, or other types of unusual events, and flag them for further investigation.\r\n\r\n[Image source]: [GAN-based Anomaly Detection in Imbalance Problems](https://paperswithcode.com/paper/gan-based-anomaly-detection-in-imbalance)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Detection AUROC","Segmentation AUROC","Segmentation AUPRO"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Detection AUROC":null,"Segmentation AUROC":null,"Segmentation AUPRO":null}},"counts":{"rows":16,"rows_with_code":11,"rows_with_paper_page":16,"rows_dated":16,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"GLASS","metrics":{"Detection AUROC":"99.6","Segmentation AUPRO":"98.2","Segmentation AUROC":"99.4"},"uses_additional_data":false,"paper_date":"2024-07-12","paper":"/paper/a-unified-anomaly-synthesis-strategy-with","paper_url":"https://arxiv.org/abs/2407.09359v1","paper_title":"A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization","code":"https://github.com/cqylunlun/glass","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"CRAS","metrics":{"Detection AUROC":"98.8","Segmentation AUROC":"98.7"},"uses_additional_data":false,"paper_date":"2025-05-23","paper":"/paper/center-aware-residual-anomaly-synthesis-for","paper_url":"https://arxiv.org/abs/2505.17551v1","paper_title":"Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection","code":"https://github.com/cqylunlun/CRAS","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"DMDD","metrics":{"Detection AUROC":"98.10","Segmentation AUPRO":"97.66","Segmentation AUROC":"98.96"},"uses_additional_data":false,"paper_date":"2024-08-07","paper":"/paper/dual-modeling-decouple-distillation-for","paper_url":"https://arxiv.org/abs/2408.03888v2","paper_title":"Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"PBAS","metrics":{"Detection AUROC":"97.7","Segmentation AUPRO":"97.1","Segmentation AUROC":"98.8"},"uses_additional_data":false,"paper_date":"2024-12-23","paper":"/paper/progressive-boundary-guided-anomaly-synthesis","paper_url":"https://arxiv.org/abs/2412.17458v1","paper_title":"Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detection","code":"https://github.com/cqylunlun/pbas","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"GLAD","metrics":{"Detection AUROC":"97.5","Segmentation AUROC":"98.7"},"uses_additional_data":false,"paper_date":"2024-06-11","paper":"/paper/glad-towards-better-reconstruction-with","paper_url":"https://arxiv.org/abs/2406.07487v3","paper_title":"GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection","code":"https://github.com/hyao1/glad","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":5,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"POUTA","metrics":{"Detection AUROC":"97.5"},"uses_additional_data":false,"paper_date":"2023-12-20","paper":"/paper/produce-once-utilize-twice-for-anomaly","paper_url":"https://arxiv.org/abs/2312.12913v1","paper_title":"Produce Once, Utilize Twice for Anomaly Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"Dinomaly","metrics":{"Detection AUROC":"97.2","Segmentation AUROC":"99.1"},"uses_additional_data":false,"paper_date":"2024-05-23","paper":"/paper/dinomaly-the-less-is-more-philosophy-in-multi","paper_url":"https://arxiv.org/abs/2405.14325v4","paper_title":"Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection","code":"https://github.com/guojiajeremy/dinomaly","n_code_links":2,"syntology":{"n_ran":9,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"RealNet","metrics":{"Detection AUROC":"96.3","Segmentation AUROC":"98.2"},"uses_additional_data":true,"paper_date":"2024-03-09","paper":"/paper/realnet-a-feature-selection-network-with","paper_url":"https://arxiv.org/abs/2403.05897v1","paper_title":"RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection","code":"https://github.com/cnulab/realnet","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"DiffusionAD","metrics":{"Detection AUROC":"96.2","Segmentation AUPRO":"95.3","Segmentation AUROC":"98.5"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/diffusionad-denoising-diffusion-for-anomaly","paper_url":"https://arxiv.org/abs/2303.08730v4","paper_title":"DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection","code":"https://github.com/huizhang0812/diffusionad","n_code_links":2,"syntology":null},{"rank_in_archive_order":10,"model":"ULSAD","metrics":{"Detection AUROC":"95.73","Segmentation AUPRO":"92.02","Segmentation AUROC":"97.45"},"uses_additional_data":false,"paper_date":"2024-10-21","paper":"/paper/revisiting-deep-feature-reconstruction-for","paper_url":"https://arxiv.org/abs/2410.16255v1","paper_title":"Revisiting Deep Feature Reconstruction for Logical and Structural Industrial Anomaly Detection","code":"https://github.com/sukanyapatra1997/ulsad-2024","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":13,"n_samples":13,"n_pointer_only_licence":13}},{"rank_in_archive_order":11,"model":"LeMO","metrics":{"Detection AUROC":"87.4","Segmentation AUPRO":"91.9","Segmentation AUROC":"97.8"},"uses_additional_data":false,"paper_date":"2023-05-25","paper":"/paper/towards-total-online-unsupervised-anomaly","paper_url":"https://arxiv.org/abs/2305.15652v1","paper_title":"Towards Total Online Unsupervised Anomaly Detection and Localization in Industrial Vision","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"FastRecon","metrics":{"Detection AUROC":"82.5","Segmentation AUROC":"97.9"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/fastrecon-few-shot-industrial-anomaly","paper_url":"http://openaccess.thecvf.com//content/ICCV2023/html/Fang_FastRecon_Few-shot_Industrial_Anomaly_Detection_via_Fast_Feature_Reconstruction_ICCV_2023_paper.html","paper_title":"FastRecon: Few-shot Industrial Anomaly Detection via Fast Feature Reconstruction","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"AdaCLIP","metrics":{"Detection AUROC":"82.5","Segmentation AUROC":"96.1"},"uses_additional_data":false,"paper_date":"2024-07-22","paper":"/paper/adaclip-adapting-clip-with-hybrid-learnable","paper_url":"https://arxiv.org/abs/2407.15795v1","paper_title":"AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection","code":"https://github.com/caoyunkang/adaclip","n_code_links":1,"syntology":{"n_ran":19,"n_unverified":9,"n_samples":28,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"PatchCore","metrics":{"Detection AUROC":"82.12","Segmentation AUROC":"95.66"},"uses_additional_data":false,"paper_date":"2021-06-15","paper":"/paper/towards-total-recall-in-industrial-anomaly","paper_url":"https://arxiv.org/abs/2106.08265v2","paper_title":"Towards Total Recall in Industrial Anomaly Detection","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":18,"syntology":{"n_ran":5,"n_unverified":31,"n_samples":36,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"KAnoCLIP","metrics":{"Detection AUROC":"77.8","Segmentation AUROC":"98.3"},"uses_additional_data":false,"paper_date":"2025-01-07","paper":"/paper/kanoclip-zero-shot-anomaly-detection-through","paper_url":"https://arxiv.org/abs/2501.03786v1","paper_title":"KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integration","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"ADSPR","metrics":{"Segmentation AUROC":"96.8"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/anomaly-detection-using-score-based","paper_url":"http://openaccess.thecvf.com//content/ICCV2023/html/Shin_Anomaly_Detection_using_Score-based_Perturbation_Resilience_ICCV_2023_paper.html","paper_title":"Anomaly Detection using Score-based Perturbation Resilience","code":"https://github.com/Lee-JongHyeon/Anomaly-Detection-using-Score-based-Perturbation-Resilience","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,795 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":7,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":57,"n_unverified":63,"n_samples":120,"n_pointer_only_licence":13,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":57,"n_unverified":63,"n_samples":120,"n_pointer_only_licence":13,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}