{"url":"/task/multi-class-anomaly-detection","name":"Multi-class Anomaly Detection","slug":"multi-class-anomaly-detection","description_markdown":"Multi-class Anomaly Detection is a task that identifies anomalies by jointly learning and detecting outliers across multiple classes, in contrast to traditional Anomaly Detection, which typically focuses on identifying anomalies within a single class.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Graphs","url":"/area/graphs"},{"name":"Methodology","url":"/area/methodology"},{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":39,"papers_with_code":20,"benchmarks":2,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/multi-class-anomaly-detection-on-mvtec-ad","slug":"multi-class-anomaly-detection-on-mvtec-ad","dataset":"MVTec AD","dataset_url":"/dataset/mvtecad","rows_in_archive":13,"metrics":["Detection AUROC","Segmentation AUROC"],"first_row_in_archive_order":{"model":"INP-Former-Large","paper_title":"Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection","paper_url":"/paper/exploring-intrinsic-normal-prototypes-within","paper_date":"2025-03-04","arxiv_id":"2503.02424","code_links":[{"title":"luow23/inp-former","url":"https://github.com/luow23/inp-former"},{"title":"septmars/DL","url":"https://github.com/septmars/DL"}],"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/multi-class-anomaly-detection-on-itdd","slug":"multi-class-anomaly-detection-on-itdd","dataset":"ITDD","dataset_url":"/dataset/itdd","rows_in_archive":1,"metrics":["Detection AUROC","Segmentation AUROC"],"first_row_in_archive_order":{"model":"CRAS","paper_title":"Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection","paper_url":"/paper/center-aware-residual-anomaly-synthesis-for","paper_date":"2025-05-23","arxiv_id":"2505.17551","code_links":[{"title":"cqylunlun/CRAS","url":"https://github.com/cqylunlun/CRAS"}],"syntology":null}},{"leaderboard":null,"slug":"multi-class-anomaly-detection-on-visa","dataset":"VisA","dataset_url":"/dataset/visa","rows_in_archive":0,"metrics":["Detection AUROC"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/mvtecad","name":"MVTecAD","full_name":"MVTEC ANOMALY DETECTION DATASET","num_papers_in_archive":402},{"url":"/dataset/visa","name":"VisA","full_name":"Visual Anomaly Dataset","num_papers_in_archive":86},{"url":"/dataset/itdd","name":"ITDD","full_name":"Industrial Textile Defect Detection","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/anomaly-detection","name":"Anomaly Detection"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":20,"of":20,"tagged_in_all":39,"items":[{"url":"/paper/mambaad-exploring-state-space-models-for","title":"MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection","date":"2024-04-09","arxiv_id":"2404.06564","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/exploring-intrinsic-normal-prototypes-within","title":"Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection","date":"2025-03-04","arxiv_id":"2503.02424","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/dinomaly-the-less-is-more-philosophy-in-multi","title":"Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection","date":"2024-05-23","arxiv_id":"2405.14325","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/center-aware-residual-anomaly-synthesis-for","title":"Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection","date":"2025-05-23","arxiv_id":"2505.17551","repositories_listed":1,"syntology":null},{"url":"/paper/omni-ad-learning-to-reconstruct-global-and","title":"Omni-AD: Learning to Reconstruct Global and Local Features for Multi-class Anomaly Detection","date":"2025-03-27","arxiv_id":"2503.21125","repositories_listed":1,"syntology":null},{"url":"/paper/uninet-a-contrastive-learning-guided-unified","title":"UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection","date":"2025-02-28","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/context-enhancement-with-reconstruction-as","title":"Context Enhancement with Reconstruction as Sequence for Unified Unsupervised Anomaly Detection","date":"2024-09-10","arxiv_id":"2409.06285","repositories_listed":1,"syntology":null},{"url":"/paper/vq-flow-taming-normalizing-flows-for-multi","title":"VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization","date":"2024-09-02","arxiv_id":"2409.00942","repositories_listed":1,"syntology":null},{"url":"/paper/a-classifier-based-approach-to-multi-class-1","title":"A Classifier-Based Approach to Multi-Class Anomaly Detection Applied to Astronomical Time-Series","date":"2024-08-05","arxiv_id":"2408.08888","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/ader-a-comprehensive-benchmark-for-multi","title":"A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detection","date":"2024-06-05","arxiv_id":"2406.03262","repositories_listed":1,"syntology":null},{"url":"/paper/attend-distill-detect-attention-aware-entropy","title":"Attend, Distill, Detect: Attention-aware Entropy Distillation for Anomaly Detection","date":"2024-05-10","arxiv_id":"2405.06467","repositories_listed":1,"syntology":null},{"url":"/paper/learning-feature-inversion-for-multi-class","title":"Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark","date":"2024-04-16","arxiv_id":"2404.10760","repositories_listed":1,"syntology":null},{"url":"/paper/a-classifier-based-approach-to-multi-class","title":"A Classifier-Based Approach to Multi-Class Anomaly Detection for Astronomical Transients","date":"2024-03-21","arxiv_id":"2403.14742","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-gaussian-mixture-normalizing","title":"Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detection","date":"2024-03-20","arxiv_id":"2403.13349","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/learning-unified-reference-representation-for","title":"Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection","date":"2024-03-18","arxiv_id":"2403.11561","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":7}},{"url":"/paper/exploring-plain-vit-reconstruction-for-multi","title":"Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection","date":"2023-12-12","arxiv_id":"2312.07495","repositories_listed":1,"syntology":null},{"url":"/paper/diad-a-diffusion-based-framework-for-multi","title":"DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection","date":"2023-12-11","arxiv_id":"2312.06607","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/hierarchical-vector-quantized-transformer-for-1","title":"Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection","date":"2023-10-22","arxiv_id":"2310.14228","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/selformaly-towards-task-agnostic-unified","title":"UniFormaly: Towards Task-Agnostic Unified Framework for Visual Anomaly Detection","date":"2023-07-24","arxiv_id":"2307.12540","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-model-for-multi-class-anomaly","title":"A Unified Model for Multi-class Anomaly Detection","date":"2022-06-08","arxiv_id":"2206.03687","repositories_listed":1,"syntology":{"n":15,"n_ran":8,"n_unverified":7,"n_pointer_only":0}}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}