{"id":"W4390886362","doi":"10.1016/j.neunet.2024.106106","title":"Self-supervised anomaly detection in computer vision and beyond: A survey and outlook","year":2024,"lang":"en","type":"article","venue":"Neural Networks","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec; Fonds de recherche du Québec – Nature et technologies; Department of Electricial and Computer Engineering, Boston University; AGE-WELL","keywords":"Anomaly detection; Computer science; Margin (machine learning); Artificial intelligence; Field (mathematics); Machine learning; Supervised learning; Anomaly (physics); Deep learning; State of art; Data science; Artificial neural network; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002521824,0.0001198468,0.0001169886,0.0001154235,0.00009740696,0.0003184084,0.0001443141,0.00009311396,0.000001943953],"category_scores_gemma":[0.000002231762,0.0001058678,0.00002622619,0.0004740492,0.0000278897,0.0003583227,0.0001766429,0.0002138413,0.000002538572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002118459,"about_ca_system_score_gemma":0.00000696608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007632207,"about_ca_topic_score_gemma":0.000179979,"domain_scores_codex":[0.9990823,0.00008400858,0.0001696575,0.00041478,0.00007895196,0.0001702779],"domain_scores_gemma":[0.9995726,0.0001205364,0.00002284541,0.0001954538,0.00002231238,0.00006629949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007991807,0.00002685706,0.00270288,0.00002087799,0.00000686135,0.00001540648,0.0001348404,0.000524938,0.0001594673,0.001028815,0.0002152393,0.9951558],"study_design_scores_gemma":[0.00009352474,0.0001490083,0.03872534,0.000009646878,0.000002391451,0.0000498131,0.000001515655,0.959894,0.00006367806,0.0003341517,0.0005654495,0.0001114881],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2237496,0.0005857515,0.7744224,0.000301529,0.0001921054,0.0002011816,0.00000109158,0.0004793324,0.00006700058],"genre_scores_gemma":[0.9863417,0.0001534953,0.01308692,0.000267075,0.0000898794,0.00002759471,0.000002329122,0.000009814016,0.00002117018],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9950444,"threshold_uncertainty_score":0.4317163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008824441086658565,"score_gpt":0.2391377088774286,"score_spread":0.23031326779077,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}