{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002905382,0.0009243231,0.001857004,0.002168075,0.0004274711,0.002424392,0.002418624,0.001646628,0.0008884955],"category_scores_gemma":[0.004599023,0.0005569087,0.000791811,0.00286577,0.001220431,0.003957252,0.001301616,0.00151948,0.0005814717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001021069,"about_ca_system_score_gemma":0.001083252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00268488,"about_ca_topic_score_gemma":0.002236044,"domain_scores_codex":[0.9986504,0.0002595744,0.00009475195,0.0004257651,0.000506119,0.00006348436],"domain_scores_gemma":[0.9963953,0.001705857,0.0003139133,0.0003287811,0.001131767,0.0001243607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008273844,0.000339674,0.004839997,0.001296477,0.0001876347,0.00005559025,0.0001032744,0.02433646,0.002895372,0.01775392,0.00597649,0.9421324],"study_design_scores_gemma":[0.00002504593,0.0004246809,0.006031262,0.0007947581,0.0002069153,0.0008517367,0.000308986,0.8136016,0.01153866,0.1088502,0.05722526,0.0001409356],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.01919845,0.2866672,0.6825847,0.00308681,0.0006109366,0.0001231539,0.0001518519,0.0009291054,0.00664791],"genre_scores_gemma":[0.3823768,0.2603863,0.3433748,0.001293338,0.003431126,0.0002047055,0.0007958038,0.0002565241,0.007880658],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.002905382,"threshold_uncertainty_score":0.0153653,"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."}}