{"url":"/sota/anomaly-detection-on-visa","task":{"name":"Anomaly Detection","url":"/task/anomaly-detection","note":null},"dataset":{"name":"VisA","url":"/dataset/visa"},"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 AUPRO (until 30% FPR)","F1-Score","Segmentation AUPRO","Segmentation AUROC"],"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 AUPRO (until 30% FPR)":null,"F1-Score":"higher","Segmentation AUPRO":null,"Segmentation AUROC":null}},"counts":{"rows":50,"rows_with_code":48,"rows_with_paper_page":49,"rows_dated":49,"rows_using_additional_data":6},"rows":[{"rank_in_archive_order":1,"model":"UniNet","metrics":{"Detection AUROC":"99.8","Segmentation AUPRO":"93.9","Segmentation AUPRO (until 30% FPR)":"93.9","Segmentation AUROC":"98.8"},"uses_additional_data":false,"paper_date":"2025-02-28","paper":"/paper/uninet-a-contrastive-learning-guided-unified","paper_url":"https://pangdatangtt.github.io/#:~:text=guided%20anomaly%20discrimination.-,Abstract,-Anomaly%20detection%20(AD","paper_title":"UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection","code":"https://github.com/pangdatangtt/UniNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"GLAD","metrics":{"Detection AUROC":"99.5","F1-Score":"98.3","Segmentation AUPRO":"94.3","Segmentation AUPRO (until 30% FPR)":"94.3","Segmentation AUROC":"98.6"},"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":3,"model":"UniNet(model-unified multi-class)","metrics":{"Detection AUROC":"99.15","F1-Score":"98.29"},"uses_additional_data":false,"paper_date":"2025-02-28","paper":"/paper/uninet-a-contrastive-learning-guided-unified","paper_url":"https://pangdatangtt.github.io/#:~:text=guided%20anomaly%20discrimination.-,Abstract,-Anomaly%20detection%20(AD","paper_title":"UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection","code":"https://github.com/pangdatangtt/UniNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Dinomaly ViT-L (model-unified multi-class)","metrics":{"Detection AUROC":"98.9","F1-Score":"96.1","Segmentation AUPRO":"94.8","Segmentation AUPRO (until 30% FPR)":"94.8","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":5,"model":"INP-Former ViT-B (model-unified multi-class)","metrics":{"Detection AUROC":"98.9","F1-Score":"96.6","Segmentation AUPRO":"94.4","Segmentation AUPRO (until 30% FPR)":"94.4","Segmentation AUROC":"98.9"},"uses_additional_data":false,"paper_date":"2025-03-04","paper":"/paper/exploring-intrinsic-normal-prototypes-within","paper_url":"https://arxiv.org/abs/2503.02424v1","paper_title":"Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection","code":"https://github.com/luow23/inp-former","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"DDAD","metrics":{"Detection AUROC":"98.9","Segmentation AUPRO (until 30% FPR)":"92.7","Segmentation AUROC":"97.6"},"uses_additional_data":false,"paper_date":"2023-05-25","paper":"/paper/anomaly-detection-with-conditioned-denoising","paper_url":"https://arxiv.org/abs/2305.15956v2","paper_title":"Anomaly Detection with Conditioned Denoising Diffusion Models","code":"https://github.com/arimousa/DDAD","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"DiffusionAD","metrics":{"Detection AUROC":"98.8","Segmentation AUPRO":"96.0","Segmentation AUPRO (until 30% FPR)":"96.0","Segmentation AUROC":"98.9"},"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":8,"model":"GLASS","metrics":{"Detection AUROC":"98.8","Segmentation AUPRO (until 30% FPR)":"92.8","Segmentation AUROC":"98.8"},"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":9,"model":"TransFusion","metrics":{"Detection AUROC":"98.7","Segmentation AUPRO (until 30% FPR)":"94.7"},"uses_additional_data":false,"paper_date":"2023-11-16","paper":"/paper/transfusion-a-transparency-based-diffusion","paper_url":"https://arxiv.org/abs/2311.09999v2","paper_title":"TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection","code":"https://github.com/maticfuc/eccv_transfusion","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"EfficientAD-M","metrics":{"Detection AUROC":"98.1","Segmentation AUPRO (until 30% FPR)":"94.0"},"uses_additional_data":false,"paper_date":"2023-03-25","paper":"/paper/efficientad-accurate-visual-anomaly-detection","paper_url":"https://arxiv.org/abs/2303.14535v3","paper_title":"EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":33,"syntology":{"n_ran":1,"n_unverified":34,"n_samples":35,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"HETMM","metrics":{"Detection AUROC":"98.1","Segmentation AUROC":"99.1"},"uses_additional_data":false,"paper_date":"2023-03-28","paper":"/paper/hard-nominal-example-aware-template-mutual","paper_url":"https://arxiv.org/abs/2303.16191v5","paper_title":"Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection","code":"https://github.com/NarcissusEx/HETMM","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"RealNet","metrics":{"Detection AUROC":"97.8","Segmentation AUROC":"98.8"},"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":13,"model":"PBAS","metrics":{"Detection AUROC":"97.7","Segmentation AUPRO":"93.3","Segmentation AUROC":"98.6"},"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":14,"model":"AnomalyDINO-S (full-shot)","metrics":{"Detection AUROC":"97.6","Segmentation AUPRO (until 30% FPR)":"96.1","Segmentation AUROC":"98.8"},"uses_additional_data":false,"paper_date":"2024-05-23","paper":"/paper/anomalydino-boosting-patch-based-few-shot","paper_url":"https://arxiv.org/abs/2405.14529v2","paper_title":"AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2","code":"https://github.com/dammsi/AnomalyDINO","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"EfficientAD-S","metrics":{"Detection AUROC":"97.5","Segmentation AUPRO (until 30% FPR)":"93.1"},"uses_additional_data":false,"paper_date":"2023-03-25","paper":"/paper/efficientad-accurate-visual-anomaly-detection","paper_url":"https://arxiv.org/abs/2303.14535v3","paper_title":"EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":33,"syntology":{"n_ran":1,"n_unverified":34,"n_samples":35,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"ReContrast","metrics":{"Detection AUROC":"97.5","Segmentation AUPRO":"92.6","Segmentation AUROC":"98.2"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"FAIRnoDTD","metrics":{"Detection AUROC":"97.1","Segmentation AUPRO (until 30% FPR)":"91.2","Segmentation AUROC":"98.7"},"uses_additional_data":false,"paper_date":"2023-09-13","paper":"/paper/fair-frequency-aware-image-restoration-for","paper_url":"https://arxiv.org/abs/2309.07068v1","paper_title":"FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection","code":"https://github.com/liutongkun/fair","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"CRAS","metrics":{"Detection AUROC":"97.0","Segmentation AUROC":"98.4"},"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":19,"model":"URD","metrics":{"Detection AUROC":"96.5","Segmentation AUPRO (until 30% FPR)":"95.1","Segmentation AUROC":"99.1"},"uses_additional_data":true,"paper_date":"2024-12-10","paper":"/paper/unlocking-the-potential-of-reverse","paper_url":"https://arxiv.org/abs/2412.07579v1","paper_title":"Unlocking the Potential of Reverse Distillation for Anomaly Detection","code":"https://github.com/hito2448/urd","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"D3AD","metrics":{"Detection AUROC":"96.0","Segmentation AUPRO (until 30% FPR)":"94.1","Segmentation AUROC":"97.9"},"uses_additional_data":false,"paper_date":"2024-01-09","paper":"/paper/d3ad-dynamic-denoising-diffusion","paper_url":"https://arxiv.org/abs/2401.04463v2","paper_title":"Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection","code":"https://github.com/JustinTebbe/D3AD","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"AST","metrics":{"Detection AUROC":"94.9","Segmentation AUPRO (until 30% FPR)":"81.5"},"uses_additional_data":false,"paper_date":"2022-10-14","paper":"/paper/asymmetric-student-teacher-networks-for","paper_url":"https://arxiv.org/abs/2210.07829v2","paper_title":"Asymmetric Student-Teacher Networks for Industrial Anomaly Detection","code":"https://github.com/marco-rudolph/ast","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"EdgRec","metrics":{"Detection AUROC":"94.2","Segmentation AUPRO (until 30% FPR)":"90.7"},"uses_additional_data":false,"paper_date":"2022-10-26","paper":"/paper/reconstruction-from-edge-image-combined-with","paper_url":"https://arxiv.org/abs/2210.14485v1","paper_title":"Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection","code":"https://github.com/liutongkun/edgrec","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"SuperSimpleNet","metrics":{"Detection AUROC":"93.4","Segmentation AUPRO":"87.4","Segmentation AUPRO (until 30% FPR)":"87.4"},"uses_additional_data":false,"paper_date":"2024-08-06","paper":"/paper/2408-03143","paper_url":"https://arxiv.org/abs/2408.03143v2","paper_title":"SuperSimpleNet: Unifying Unsupervised and Supervised Learning for Fast and Reliable Surface Defect Detection","code":"https://github.com/open-edge-platform/anomalib","n_code_links":2,"syntology":null},{"rank_in_archive_order":24,"model":"Student-Teacher","metrics":{"Detection AUROC":"93.2"},"uses_additional_data":false,"paper_date":"2019-11-06","paper":"/paper/uninformed-students-student-teacher-anomaly","paper_url":"https://arxiv.org/abs/1911.02357v2","paper_title":"Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings","code":"https://github.com/denguir/student-teacher-anomaly-detection","n_code_links":3,"syntology":{"n_ran":8,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":3}},{"rank_in_archive_order":25,"model":"MuSc (zero-shot)","metrics":{"Detection AUROC":"92.8","Segmentation AUPRO":"92.7","Segmentation AUPRO (until 30% FPR)":"92.7","Segmentation AUROC":"98.8"},"uses_additional_data":false,"paper_date":"2024-01-30","paper":"/paper/musc-zero-shot-industrial-anomaly","paper_url":"https://arxiv.org/abs/2401.16753v1","paper_title":"MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images","code":"https://github.com/xrli-U/MuSc","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"AnomalyDINO-S (4-shot)","metrics":{"Detection AUROC":"92.6","Segmentation AUPRO (until 30% FPR)":"94.1","Segmentation AUROC":"98.2"},"uses_additional_data":false,"paper_date":"2024-05-23","paper":"/paper/anomalydino-boosting-patch-based-few-shot","paper_url":"https://arxiv.org/abs/2405.14529v2","paper_title":"AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2","code":"https://github.com/dammsi/AnomalyDINO","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":27,"model":"CFA","metrics":{"Detection AUROC":"92.0","Segmentation AUPRO (until 30% FPR)":"55.1"},"uses_additional_data":false,"paper_date":"2022-06-09","paper":"/paper/cfa-coupled-hypersphere-based-feature","paper_url":"https://arxiv.org/abs/2206.04325v1","paper_title":"CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":2,"syntology":null},{"rank_in_archive_order":28,"model":"CFLOW","metrics":{"Detection AUROC":"91.5"},"uses_additional_data":false,"paper_date":"2021-07-27","paper":"/paper/cflow-ad-real-time-unsupervised-anomaly","paper_url":"https://arxiv.org/abs/2107.12571v1","paper_title":"CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows","code":"https://github.com/openvinotoolkit/anomalib/tree/development/anomalib/models/cflow","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":9,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":29,"model":"AnomalyDINO-S (2-shot)","metrics":{"Detection AUROC":"89.7","Segmentation AUPRO (until 30% FPR)":"93.4","Segmentation AUROC":"98"},"uses_additional_data":false,"paper_date":"2024-05-23","paper":"/paper/anomalydino-boosting-patch-based-few-shot","paper_url":"https://arxiv.org/abs/2405.14529v2","paper_title":"AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2","code":"https://github.com/dammsi/AnomalyDINO","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"GCAD","metrics":{"Detection AUROC":"89.1","Segmentation AUPRO (until 30% FPR)":"83.7"},"uses_additional_data":false,"paper_date":"2022-02-22","paper":"/paper/beyond-dents-and-scratches-logical","paper_url":"https://link.springer.com/article/10.1007/s11263-022-01578-9","paper_title":"Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":31,"model":"SPD","metrics":{"Detection AUROC":"87.8"},"uses_additional_data":false,"paper_date":"2022-07-28","paper":"/paper/spot-the-difference-self-supervised-pre","paper_url":"https://arxiv.org/abs/2207.14315v1","paper_title":"SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation","code":"https://github.com/amazon-science/spot-diff","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"AnomalyDINO-S (1-shot)","metrics":{"Detection AUROC":"87.4","Segmentation AUPRO (until 30% FPR)":"92.5","Segmentation AUROC":"97.8"},"uses_additional_data":false,"paper_date":"2024-05-23","paper":"/paper/anomalydino-boosting-patch-based-few-shot","paper_url":"https://arxiv.org/abs/2405.14529v2","paper_title":"AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2","code":"https://github.com/dammsi/AnomalyDINO","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"WinCLIP+ (4-shot)","metrics":{"Detection AUROC":"87.3","Segmentation AUPRO":"87.6","Segmentation AUPRO (until 30% FPR)":"87.6"},"uses_additional_data":false,"paper_date":"2023-03-26","paper":"/paper/winclip-zero-few-shot-anomaly-classification","paper_url":"https://arxiv.org/abs/2303.14814v1","paper_title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":7,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":34,"model":"AdaCLIP","metrics":{"Detection AUROC":"85.8","Segmentation AUROC":"95.5"},"uses_additional_data":true,"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":35,"model":"WinCLIP+ (2-shot)","metrics":{"Detection AUROC":"84.6","Segmentation AUPRO":"86.2","Segmentation AUPRO (until 30% FPR)":"86.2"},"uses_additional_data":false,"paper_date":"2023-03-26","paper":"/paper/winclip-zero-few-shot-anomaly-classification","paper_url":"https://arxiv.org/abs/2303.14814v1","paper_title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":7,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":36,"model":"WinCLIP+ (1-shot)","metrics":{"Detection AUROC":"83.8","Segmentation AUPRO":"85.1","Segmentation AUPRO (until 30% FPR)":"85.1"},"uses_additional_data":false,"paper_date":"2023-03-26","paper":"/paper/winclip-zero-few-shot-anomaly-classification","paper_url":"https://arxiv.org/abs/2303.14814v1","paper_title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":7,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":37,"model":"STPM","metrics":{"Detection AUROC":"83.3","Segmentation AUPRO (until 30% FPR)":"62.0"},"uses_additional_data":false,"paper_date":"2021-03-07","paper":"/paper/student-teacher-feature-pyramid-matching-for","paper_url":"https://arxiv.org/abs/2103.04257v3","paper_title":"Student-Teacher Feature Pyramid Matching for Anomaly Detection","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":10,"syntology":null},{"rank_in_archive_order":38,"model":"SPADE","metrics":{"Detection AUROC":"82.1","Segmentation AUPRO (until 30% FPR)":"65.9"},"uses_additional_data":false,"paper_date":"2020-05-05","paper":"/paper/sub-image-anomaly-detection-with-deep-pyramid","paper_url":"https://arxiv.org/abs/2005.02357v3","paper_title":"Sub-Image Anomaly Detection with Deep Pyramid Correspondences","code":"https://github.com/byungjae89/SPADE-pytorch","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":39,"model":"AnomalyCLIP","metrics":{"Detection AUROC":"82.1","Segmentation AUPRO":"87.0","Segmentation AUROC":"95.5"},"uses_additional_data":true,"paper_date":"2023-10-29","paper":"/paper/anomalyclip-object-agnostic-prompt-learning","paper_url":"https://arxiv.org/abs/2310.18961v9","paper_title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection","code":"https://github.com/zqhang/anomalyclip","n_code_links":3,"syntology":{"n_ran":14,"n_unverified":18,"n_samples":32,"n_pointer_only_licence":0}},{"rank_in_archive_order":40,"model":"AnoDDPM","metrics":{"Detection AUROC":"78.2","Segmentation AUPRO (until 30% FPR)":"60.5"},"uses_additional_data":false,"paper_date":"2022-06-30","paper":"/paper/anoddpm-anomaly-detection-with-denoising","paper_url":"https://openaccess.thecvf.com/content/CVPR2022W/NTIRE/html/Wyatt_AnoDDPM_Anomaly_Detection_With_Denoising_Diffusion_Probabilistic_Models_Using_Simplex_CVPRW_2022_paper.html","paper_title":"AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise","code":"https://github.com/julian-wyatt/anoddpm","n_code_links":1,"syntology":null},{"rank_in_archive_order":41,"model":"WinCLIP (0-shot)","metrics":{"Detection AUROC":"78.1","Segmentation AUPRO":"56.8","Segmentation AUPRO (until 30% FPR)":"56.8"},"uses_additional_data":false,"paper_date":"2023-03-26","paper":"/paper/winclip-zero-few-shot-anomaly-classification","paper_url":"https://arxiv.org/abs/2303.14814v1","paper_title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":7,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":42,"model":"APRIL-GAN","metrics":{"Detection AUROC":"78.0","F1-Score":"32.3","Segmentation AUPRO":"86.8","Segmentation AUROC":"94.2"},"uses_additional_data":true,"paper_date":"2023-05-27","paper":"/paper/a-zero-few-shot-anomaly-classification-and","paper_url":"https://arxiv.org/abs/2305.17382v3","paper_title":"APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD","code":"https://github.com/bychelsea/vand-april-gan","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":6,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":43,"model":"PaDiM","metrics":{"Segmentation AUPRO (until 30% FPR)":"85.9"},"uses_additional_data":false,"paper_date":"2020-11-17","paper":"/paper/padim-a-patch-distribution-modeling-framework","paper_url":"https://arxiv.org/abs/2011.08785v1","paper_title":"PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":26,"syntology":{"n_ran":7,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":3}},{"rank_in_archive_order":44,"model":"DRAEM","metrics":{"Segmentation AUPRO (until 30% FPR)":"73.1"},"uses_additional_data":false,"paper_date":"2021-08-17","paper":"/paper/draem-a-discriminatively-trained","paper_url":"https://arxiv.org/abs/2108.07610v2","paper_title":"DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection","code":"https://github.com/openvinotoolkit/anomalib/tree/development/anomalib/models/draem","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":45,"model":"Reverse Distillation","metrics":{"Segmentation AUPRO (until 30% FPR)":"70.9"},"uses_additional_data":false,"paper_date":"2022-01-26","paper":"/paper/anomaly-detection-via-reverse-distillation","paper_url":"https://arxiv.org/abs/2201.10703v2","paper_title":"Anomaly Detection via Reverse Distillation from One-Class Embedding","code":"https://github.com/openvinotoolkit/anomalib/tree/development/anomalib/models/reverse_distillation","n_code_links":5,"syntology":{"n_ran":14,"n_unverified":4,"n_samples":18,"n_pointer_only_licence":15}},{"rank_in_archive_order":46,"model":"DSR","metrics":{"Segmentation AUPRO (until 30% FPR)":"68.1"},"uses_additional_data":false,"paper_date":"2022-08-02","paper":"/paper/dsr-a-dual-subspace-re-projection-network-for","paper_url":"https://arxiv.org/abs/2208.01521v2","paper_title":"DSR -- A dual subspace re-projection network for surface anomaly detection","code":"https://github.com/vitjanz/dsr_anomaly_detection","n_code_links":1,"syntology":null},{"rank_in_archive_order":47,"model":"FAVAE","metrics":{"Segmentation AUPRO (until 30% FPR)":"67.9"},"uses_additional_data":false,"paper_date":"2020-08-12","paper":"/paper/anomaly-localization-by-modeling-perceptual","paper_url":"https://arxiv.org/abs/2008.05369v1","paper_title":"Anomaly localization by modeling perceptual features","code":"https://github.com/xiahaifeng1995/FAVAE-anomaly-detection-localization-master","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":48,"model":"FastFlow","metrics":{"Segmentation AUPRO (until 30% FPR)":"59.8"},"uses_additional_data":false,"paper_date":"2021-11-15","paper":"/paper/fastflow-unsupervised-anomaly-detection-and","paper_url":"https://arxiv.org/abs/2111.07677v2","paper_title":"FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows","code":"https://github.com/openvinotoolkit/anomalib/tree/main/src/anomalib/models/fastflow","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":49,"model":"SAA+","metrics":{"F1-Score":"27.07"},"uses_additional_data":false,"paper_date":"2023-05-18","paper":"/paper/segment-any-anomaly-without-training-via","paper_url":"https://arxiv.org/abs/2305.10724v1","paper_title":"Segment Any Anomaly without Training via Hybrid Prompt Regularization","code":"https://github.com/caoyunkang/groundedsam-zero-shot-anomaly-detection","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":50,"model":"VCP-CLIP","metrics":{"Segmentation AUPRO":"90.7","Segmentation AUROC":"95.7"},"uses_additional_data":true,"paper_date":"2024-07-17","paper":"/paper/vcp-clip-a-visual-context-prompting-model-for","paper_url":"https://arxiv.org/abs/2407.12276v1","paper_title":"VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation","code":"https://github.com/xiaozhen228/vcp-clip","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 6,264 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":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"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":30,"rows_with_any_sample_ran":27,"distinct_papers_with_graph_line":23,"distinct_papers_with_any_sample_ran":20,"samples_over_distinct_papers":{"n_ran":130,"n_unverified":128,"n_samples":258,"n_pointer_only_licence":21,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":173,"n_unverified":192,"n_samples":365,"n_pointer_only_licence":21,"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"}}}