{"url":"/task/unsupervised-anomaly-detection","name":"Unsupervised Anomaly Detection","slug":"unsupervised-anomaly-detection","description_markdown":"The objective of **Unsupervised Anomaly Detection** is to detect previously unseen rare objects or events without any prior knowledge about these. The only information available is that the percentage of anomalies in the dataset is small, usually less than 1%. Since anomalies are rare and unknown to the user at training time, anomaly detection in most cases boils down to the problem of modelling the normal data distribution and defining a measurement in this space in order to classify samples as anomalous or normal. In high-dimensional data such as images, distances in the original space quickly lose descriptive power (curse of dimensionality) and a mapping to some more suitable space is required.\n\n\n<span class=\"description-source\">Source: [Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training ](https://arxiv.org/abs/1905.11034)</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Graphs","url":"/area/graphs"},{"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":506,"papers_with_code":226,"benchmarks":18,"benchmark_tables_in_archive":18,"benchmark_tables_shown":18,"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":27,"subtasks":5,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/unsupervised-anomaly-detection-on-anoshift","slug":"unsupervised-anomaly-detection-on-anoshift","dataset":"AnoShift","dataset_url":"/dataset/anoshift","rows_in_archive":15,"metrics":["ROC-AUC FAR","ROC-AUC IID","ROC-AUC NEAR","ROC-AUC-ID (In-Distribution setup)"],"first_row_in_archive_order":{"model":"ACR-NTL (zero-shot, test anomaly ratio=1%)","paper_title":"Zero-Shot Anomaly Detection via Batch Normalization","paper_url":"/paper/zero-shot-anomaly-detection-via-batch-1","paper_date":"2023-02-15","arxiv_id":"2302.07849","code_links":[{"title":"aodongli/zero-shot-ad-via-batch-norm","url":"https://github.com/aodongli/zero-shot-ad-via-batch-norm"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-smap","slug":"unsupervised-anomaly-detection-on-smap","dataset":"SMAP","dataset_url":"/dataset/smap","rows_in_archive":9,"metrics":["F1","Precision","Recall","AUC"],"first_row_in_archive_order":{"model":"DFM (flow matching)","paper_title":"DFM: Interpolant-free Dual Flow Matching","paper_url":"/paper/dfm-interpolant-free-dual-flow-matching","paper_date":"2024-10-11","arxiv_id":"2410.09246","code_links":[],"syntology":null}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-vehicle","slug":"unsupervised-anomaly-detection-on-vehicle","dataset":"Vehicle Claims","dataset_url":"/dataset/vehicle-claims","rows_in_archive":9,"metrics":["AUC"],"first_row_in_archive_order":{"model":"SOM","paper_title":"Unsupervised Anomaly Detection for Auditing Data and Impact of Categorical Encodings","paper_url":"/paper/unsupervised-anomaly-detection-for-auditing","paper_date":"2022-10-25","arxiv_id":"2210.14056","code_links":[{"title":"ajaychawda58/uadad","url":"https://github.com/ajaychawda58/uadad"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on","slug":"unsupervised-anomaly-detection-on","dataset":"KolektorSDD2","dataset_url":"/dataset/kolektorsdd2","rows_in_archive":3,"metrics":["Segmentation AP","Segmentation AUROC","Detection AP","Segmentation AUPRO"],"first_row_in_archive_order":{"model":"WeakREST-Un","paper_title":"Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformers","paper_url":"/paper/efficient-anomaly-detection-with-budget","paper_date":"2023-06-06","arxiv_id":"2306.03492","code_links":[],"syntology":null}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-20news-1","slug":"unsupervised-anomaly-detection-on-20news-1","dataset":"20NEWS","dataset_url":null,"rows_in_archive":1,"metrics":["AUC (outlier ratio = 0.5)"],"first_row_in_archive_order":{"model":"RSRAE","paper_title":"Robust Subspace Recovery Layer for Unsupervised Anomaly Detection","paper_url":"/paper/robust-subspace-recovery-layer-for","paper_date":"2019-03-30","arxiv_id":"1904.00152","code_links":[{"title":"dmzou/RSRAE","url":"https://github.com/dmzou/RSRAE"},{"title":"marrrcin/rsrlayer-pytorch","url":"https://github.com/marrrcin/rsrlayer-pytorch"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-aebad-s","slug":"unsupervised-anomaly-detection-on-aebad-s","dataset":"AeBAD-S","dataset_url":"/dataset/aebad","rows_in_archive":1,"metrics":["Detection AUROC"],"first_row_in_archive_order":{"model":"MSFR","paper_title":"Multi-scale feature reconstruction network for industrial anomaly detection","paper_url":"/paper/multi-scale-feature-reconstruction-network","paper_date":"2024-10-23","arxiv_id":null,"code_links":[{"title":"Ehteshamciitwah/MSFR","url":"https://github.com/Ehteshamciitwah/MSFR"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-caltech-101-1","slug":"unsupervised-anomaly-detection-on-caltech-101-1","dataset":"Caltech-101","dataset_url":"/dataset/caltech-101","rows_in_archive":1,"metrics":["AUC (outlier ratio = 0.5)"],"first_row_in_archive_order":{"model":"RSRAE","paper_title":"Robust Subspace Recovery Layer for Unsupervised Anomaly Detection","paper_url":"/paper/robust-subspace-recovery-layer-for","paper_date":"2019-03-30","arxiv_id":"1904.00152","code_links":[{"title":"dmzou/RSRAE","url":"https://github.com/dmzou/RSRAE"},{"title":"marrrcin/rsrlayer-pytorch","url":"https://github.com/marrrcin/rsrlayer-pytorch"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-dagm2007","slug":"unsupervised-anomaly-detection-on-dagm2007","dataset":"DAGM2007","dataset_url":"/dataset/dagm2007","rows_in_archive":1,"metrics":["Detection AUROC"],"first_row_in_archive_order":{"model":"DiffusionAD","paper_title":"DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection","paper_url":"/paper/diffusionad-denoising-diffusion-for-anomaly","paper_date":"2023-03-15","arxiv_id":"2303.08730","code_links":[{"title":"huizhang0812/diffusionad","url":"https://github.com/huizhang0812/diffusionad"},{"title":"HuiZhang0812/DiffusionAD-Denoising-Diffusion-for-Anomaly-Detection","url":"https://github.com/HuiZhang0812/DiffusionAD-Denoising-Diffusion-for-Anomaly-Detection"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-ecg5000","slug":"unsupervised-anomaly-detection-on-ecg5000","dataset":"ECG5000","dataset_url":"/dataset/ecg5000","rows_in_archive":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"VRAE+SVM","paper_title":"Learning Representations from Healthcare Time Series Data for Unsupervised Anomaly Detection","paper_url":"/paper/learning-representations-from-healthcare-time","paper_date":"2019-04-04","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-fashion-1","slug":"unsupervised-anomaly-detection-on-fashion-1","dataset":"Fashion-MNIST","dataset_url":"/dataset/fashion-mnist","rows_in_archive":1,"metrics":["AUC (outlier ratio = 0.5)"],"first_row_in_archive_order":{"model":"RSRAE","paper_title":"Robust Subspace Recovery Layer for Unsupervised Anomaly Detection","paper_url":"/paper/robust-subspace-recovery-layer-for","paper_date":"2019-03-30","arxiv_id":"1904.00152","code_links":[{"title":"dmzou/RSRAE","url":"https://github.com/dmzou/RSRAE"},{"title":"marrrcin/rsrlayer-pytorch","url":"https://github.com/marrrcin/rsrlayer-pytorch"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-kolektorsdd","slug":"unsupervised-anomaly-detection-on-kolektorsdd","dataset":"KolektorSDD","dataset_url":"/dataset/kolektorsdd","rows_in_archive":1,"metrics":["Segmentation AUROC"],"first_row_in_archive_order":{"model":"Semi-orthogonal","paper_title":"Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation","paper_url":"/paper/semi-orthogonal-embedding-for-efficient","paper_date":"2021-05-31","arxiv_id":"2105.14737","code_links":[{"title":"jnhwkim/orthoad","url":"https://github.com/jnhwkim/orthoad"},{"title":"Ultranity/Anomaly.Paddle","url":"https://github.com/Ultranity/Anomaly.Paddle"},{"title":"Pangoraw/SemiOrthogonal","url":"https://github.com/Pangoraw/SemiOrthogonal"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-mnist-1","slug":"unsupervised-anomaly-detection-on-mnist-1","dataset":"MNIST","dataset_url":"/dataset/mnist","rows_in_archive":1,"metrics":["AUROC"],"first_row_in_archive_order":{"model":"LVAD","paper_title":"Locally varying distance transform for unsupervised visual anomaly detection","paper_url":"/paper/locally-varying-distance-transform-for","paper_date":"2022-10-23","arxiv_id":null,"code_links":[{"title":"wen-yan-lin/LVAD-Locally-Varying-Anomaly-Detection","url":"https://github.com/wen-yan-lin/LVAD-Locally-Varying-Anomaly-Detection"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-pronto","slug":"unsupervised-anomaly-detection-on-pronto","dataset":"PRONTO","dataset_url":"/dataset/pronto","rows_in_archive":1,"metrics":["AUC","Best Delay","Best F1","F1"],"first_row_in_archive_order":{"model":"DyEdgeGAT","paper_title":"DyEdgeGAT: Dynamic Edge via Graph Attention for Early Fault Detection in IIoT Systems","paper_url":"/paper/dynamic-graph-attention-for-anomaly-detection","paper_date":"2023-07-07","arxiv_id":"2307.03761","code_links":[{"title":"mengjiezhao/dyedgegat","url":"https://github.com/mengjiezhao/dyedgegat"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-reuters-1","slug":"unsupervised-anomaly-detection-on-reuters-1","dataset":"Reuters-21578","dataset_url":"/dataset/reuters-21578","rows_in_archive":1,"metrics":["AUC (outlier ratio = 0.5)"],"first_row_in_archive_order":{"model":"RSRAE","paper_title":"Robust Subspace Recovery Layer for Unsupervised Anomaly Detection","paper_url":"/paper/robust-subspace-recovery-layer-for","paper_date":"2019-03-30","arxiv_id":"1904.00152","code_links":[{"title":"dmzou/RSRAE","url":"https://github.com/dmzou/RSRAE"},{"title":"marrrcin/rsrlayer-pytorch","url":"https://github.com/marrrcin/rsrlayer-pytorch"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-smd","slug":"unsupervised-anomaly-detection-on-smd","dataset":"SMD","dataset_url":"/dataset/smd","rows_in_archive":1,"metrics":["Precision"],"first_row_in_archive_order":{"model":"TranAD","paper_title":"TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data","paper_url":"/paper/tranad-deep-transformer-networks-for-anomaly","paper_date":"2022-01-18","arxiv_id":"2201.07284","code_links":[{"title":"imperial-qore/tranad","url":"https://github.com/imperial-qore/tranad"},{"title":"xuhongzuo/DeepOD","url":"https://github.com/xuhongzuo/DeepOD"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":1}}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-stl-10","slug":"unsupervised-anomaly-detection-on-stl-10","dataset":"STL-10","dataset_url":"/dataset/stl-10","rows_in_archive":1,"metrics":["AUC-ROC"],"first_row_in_archive_order":{"model":"LVAD","paper_title":"Locally varying distance transform for unsupervised visual anomaly detection","paper_url":"/paper/locally-varying-distance-transform-for","paper_date":"2022-10-23","arxiv_id":null,"code_links":[{"title":"wen-yan-lin/LVAD-Locally-Varying-Anomaly-Detection","url":"https://github.com/wen-yan-lin/LVAD-Locally-Varying-Anomaly-Detection"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-synthetic","slug":"unsupervised-anomaly-detection-on-synthetic","dataset":"Synthetic","dataset_url":null,"rows_in_archive":1,"metrics":["AUC","Best Delay","Best F1","F1"],"first_row_in_archive_order":{"model":"DyEdgeGAT","paper_title":"DyEdgeGAT: Dynamic Edge via Graph Attention for Early Fault Detection in IIoT Systems","paper_url":"/paper/dynamic-graph-attention-for-anomaly-detection","paper_date":"2023-07-07","arxiv_id":"2307.03761","code_links":[{"title":"mengjiezhao/dyedgegat","url":"https://github.com/mengjiezhao/dyedgegat"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-timo","slug":"unsupervised-anomaly-detection-on-timo","dataset":"TIMo","dataset_url":null,"rows_in_archive":1,"metrics":["AUROC"],"first_row_in_archive_order":{"model":"P-CAE W-MSE (Tilted View)","paper_title":"Unsupervised Anomaly Detection from Time-of-Flight Depth Images","paper_url":"/paper/unsupervised-anomaly-detection-from-time-of","paper_date":"2022-03-02","arxiv_id":"2203.01052","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/fashion-mnist","name":"Fashion-MNIST","full_name":"","num_papers_in_archive":3202},{"url":"/dataset/stl-10","name":"STL-10","full_name":"Self-Taught Learning 10","num_papers_in_archive":1092},{"url":"/dataset/caltech-101","name":"Caltech-101","full_name":"","num_papers_in_archive":709},{"url":"/dataset/mvtecad","name":"MVTecAD","full_name":"MVTEC ANOMALY DETECTION DATASET","num_papers_in_archive":402},{"url":"/dataset/smap","name":"SMAP","full_name":"Soil Moisture Active Passive","num_papers_in_archive":127},{"url":"/dataset/reuters-21578","name":"Reuters-21578","full_name":"","num_papers_in_archive":66},{"url":"/dataset/mimii","name":"MIMII","full_name":"","num_papers_in_archive":40},{"url":"/dataset/mvtec-loco-ad","name":"MVTec LOCO AD","full_name":"MVTec Logical Constraints Anomaly Detection","num_papers_in_archive":32},{"url":"/dataset/kolektorsdd","name":"KolektorSDD","full_name":"Kolektor Surface-Defect Dataset","num_papers_in_archive":15},{"url":"/dataset/kolektorsdd2","name":"KolektorSDD2","full_name":"Kolektor Surface-Defect Dataset 2","num_papers_in_archive":15},{"url":"/dataset/toyadmos","name":"ToyADMOS","full_name":null,"num_papers_in_archive":15},{"url":"/dataset/aebad","name":"AeBAD","full_name":"Aero-engine Blade Anomaly Detection Dataset","num_papers_in_archive":11},{"url":"/dataset/smd","name":"SMD","full_name":"Server Machine Dataset","num_papers_in_archive":10},{"url":"/dataset/chad","name":"CHAD","full_name":"Charlotte Anomaly Dataset","num_papers_in_archive":7},{"url":"/dataset/ubi-fights","name":"UBI-Fights","full_name":"Abnormal Event Detection Dataset","num_papers_in_archive":7},{"url":"/dataset/anoshift","name":"AnoShift","full_name":"AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection","num_papers_in_archive":6},{"url":"/dataset/dagm2007","name":"DAGM2007","full_name":"DAGM2007","num_papers_in_archive":6},{"url":"/dataset/ecg5000","name":"ECG5000","full_name":"ECG5000","num_papers_in_archive":6},{"url":"/dataset/failure-dataset-openstack","name":"Failure-Dataset-OpenStack","full_name":"","num_papers_in_archive":2},{"url":"/dataset/miad","name":"MIAD","full_name":"","num_papers_in_archive":2},{"url":"/dataset/pose-agnostic-anomaly-detection-dataset","name":"PAD Dataset","full_name":"Pose-agnostic/Multi-pose Anomaly Detection Dataset","num_papers_in_archive":2},{"url":"/dataset/vehicle-claims","name":"Vehicle Claims","full_name":"","num_papers_in_archive":2},{"url":"/dataset/isp-ad","name":"ISP-AD","full_name":"The Industrial Screen Printing Anomaly Detection Dataset","num_papers_in_archive":1},{"url":"/dataset/itd","name":"ITD","full_name":"Industrial Textile Dataset","num_papers_in_archive":1},{"url":"/dataset/pronto","name":"PRONTO","full_name":"PRONTO heterogeneous benchmark dataset","num_papers_in_archive":1},{"url":"/dataset/spot-10","name":"SPOT-10","full_name":"Animal Pattern Benchmark Dataset for Machine Learning Algorithms","num_papers_in_archive":1}],"subtasks":[{"url":"/task/anomaly-detection-at-30-anomaly","name":"Anomaly Detection at 30% anomaly"},{"url":"/task/anomaly-detection-at-various-anomaly","name":"Anomaly Detection at Various Anomaly Percentages"},{"url":"/task/root-cause-ranking","name":"Root Cause Ranking"},{"url":"/task/unsupervised-anomaly-detection-with-specified","name":"Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly"},{"url":"/task/unsupervised-contextual-anomaly-detection","name":"Unsupervised Contextual Anomaly Detection"}],"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":30,"of":226,"tagged_in_all":506,"items":[{"url":"/paper/efficientad-accurate-visual-anomaly-detection","title":"EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies","date":"2023-03-25","arxiv_id":"2303.14535","repositories_listed":33,"syntology":{"n":35,"n_ran":1,"n_unverified":34,"n_pointer_only":0}},{"url":"/paper/glow-generative-flow-with-invertible-1x1","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","date":"2018-07-09","arxiv_id":"1807.03039","repositories_listed":27,"syntology":{"n":129,"n_ran":75,"n_unverified":54,"n_pointer_only":44}},{"url":"/paper/padim-a-patch-distribution-modeling-framework","title":"PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization","date":"2020-11-17","arxiv_id":"2011.08785","repositories_listed":26,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/towards-total-recall-in-industrial-anomaly","title":"Towards Total Recall in Industrial Anomaly Detection","date":"2021-06-15","arxiv_id":"2106.08265","repositories_listed":18,"syntology":{"n":36,"n_ran":5,"n_unverified":31,"n_pointer_only":0}},{"url":"/paper/unsupervised-anomaly-detection-with","title":"Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery","date":"2017-03-17","arxiv_id":"1703.05921","repositories_listed":18,"syntology":{"n":11,"n_ran":3,"n_unverified":8,"n_pointer_only":3}},{"url":"/paper/student-teacher-feature-pyramid-matching-for","title":"Student-Teacher Feature Pyramid Matching for Anomaly Detection","date":"2021-03-07","arxiv_id":"2103.04257","repositories_listed":10,"syntology":null},{"url":"/paper/unsupervised-anomaly-detection-via","title":"Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications","date":"2018-02-12","arxiv_id":"1802.03903","repositories_listed":10,"syntology":null},{"url":"/paper/anomaly-detection-via-reverse-distillation","title":"Anomaly Detection via Reverse Distillation from One-Class Embedding","date":"2022-01-26","arxiv_id":"2201.10703","repositories_listed":5,"syntology":{"n":18,"n_ran":14,"n_unverified":4,"n_pointer_only":15}},{"url":"/paper/fastflow-unsupervised-anomaly-detection-and","title":"FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows","date":"2021-11-15","arxiv_id":"2111.07677","repositories_listed":5,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/tadgan-time-series-anomaly-detection-using","title":"TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks","date":"2020-09-16","arxiv_id":"2009.07769","repositories_listed":5,"syntology":null},{"url":"/paper/sub-image-anomaly-detection-with-deep-pyramid","title":"Sub-Image Anomaly Detection with Deep Pyramid Correspondences","date":"2020-05-05","arxiv_id":"2005.02357","repositories_listed":5,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/memorizing-normality-to-detect-anomaly-memory","title":"Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection","date":"2019-04-04","arxiv_id":"1904.02639","repositories_listed":5,"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/a-deep-neural-network-for-unsupervised","title":"A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data","date":"2018-11-20","arxiv_id":"1811.08055","repositories_listed":5,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/band-selection-with-higher-order-multivariate","title":"Band selection with Higher Order Multivariate Cumulants for small target detection in hyperspectral images","date":"2018-08-10","arxiv_id":"1808.03513","repositories_listed":5,"syntology":null},{"url":"/paper/graph-augmented-normalizing-flows-for-anomaly-1","title":"Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series","date":"2022-02-16","arxiv_id":"2202.07857","repositories_listed":4,"syntology":{"n":24,"n_ran":8,"n_unverified":16,"n_pointer_only":10}},{"url":"/paper/learning-timestamp-level-representations-for","title":"TS2Vec: Towards Universal Representation of Time Series","date":"2021-06-19","arxiv_id":"2106.10466","repositories_listed":4,"syntology":{"n":23,"n_ran":11,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/probabilistic-auto-encoder","title":"Probabilistic Autoencoder","date":"2020-06-09","arxiv_id":"2006.05479","repositories_listed":4,"syntology":{"n":13,"n_ran":1,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/weakly-supervised-deep-anomaly-detection-with","title":"Deep Weakly-supervised Anomaly Detection","date":"2019-10-30","arxiv_id":"1910.13601","repositories_listed":4,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/using-self-supervised-learning-can-improve","title":"Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty","date":"2019-06-28","arxiv_id":"1906.12340","repositories_listed":4,"syntology":{"n":12,"n_ran":5,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/deepant-a-deep-learning-approach-for","title":"DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series","date":"2018-12-19","arxiv_id":null,"repositories_listed":4,"syntology":null},{"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/guided-reconstruction-with-conditioned","title":"Guided Reconstruction with Conditioned Diffusion Models for Unsupervised Anomaly Detection in Brain MRIs","date":"2023-12-07","arxiv_id":"2312.04215","repositories_listed":3,"syntology":null},{"url":"/paper/estimating-the-contamination-factor-s","title":"Estimating the Contamination Factor's Distribution in Unsupervised Anomaly Detection","date":"2022-10-19","arxiv_id":"2210.10487","repositories_listed":3,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/draem-a-discriminatively-trained","title":"DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection","date":"2021-08-17","arxiv_id":"2108.07610","repositories_listed":3,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/cflow-ad-real-time-unsupervised-anomaly","title":"CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows","date":"2021-07-27","arxiv_id":"2107.12571","repositories_listed":3,"syntology":{"n":12,"n_ran":3,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/semi-orthogonal-embedding-for-efficient","title":"Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation","date":"2021-05-31","arxiv_id":"2105.14737","repositories_listed":3,"syntology":null},{"url":"/paper/uninformed-students-student-teacher-anomaly","title":"Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings","date":"2019-11-06","arxiv_id":"1911.02357","repositories_listed":3,"syntology":{"n":8,"n_ran":8,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/f-anogan-fast-unsupervised-anomaly-detection","title":"f-AnoGAN: Fast Unsupervised Anomaly Detection with Generative Adversarial Networks","date":"2019-01-30","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/a-unified-anomaly-synthesis-strategy-with","title":"A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization","date":"2024-07-12","arxiv_id":"2407.09359","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"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}}],"syntology_records":22,"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"}}