{"id":"W2990943125","doi":"10.48550/arxiv.1911.10608","title":"AnoNet: Weakly Supervised Anomaly Detection in Textured Surfaces","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Initialization; Anomaly detection; Computer science; Anomaly (physics); Artificial intelligence; Pattern recognition (psychology); Convolutional neural network; Computation; Enhanced Data Rates for GSM Evolution; Algorithm","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0005033814,0.0009913103,0.0007843475,0.0007660767,0.0003162415,0.0006865577,0.002167806,0.0009371784,0.003046999],"category_scores_gemma":[0.002070594,0.0004818256,0.0008109624,0.0004128696,0.0004414866,0.001241025,0.001363672,0.001104585,0.001049136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006142518,"about_ca_system_score_gemma":0.0005523075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005421382,"about_ca_topic_score_gemma":0.007479243,"domain_scores_codex":[0.9996555,0.00003491048,0.00001254768,0.0001162295,0.0001271685,0.00005372726],"domain_scores_gemma":[0.9993508,0.0002120728,0.00006038981,0.0001496512,0.0001697757,0.00005720374],"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":[0.0009740607,0.0003693514,0.007549556,0.0003085339,0.0001953431,0.0004916215,0.0002085497,0.2407405,0.07280251,0.00283275,0.01761711,0.6559101],"study_design_scores_gemma":[0.00001300874,0.00005075477,0.0007608238,0.000005065789,0.000006161805,0.00006615139,0.00001709392,0.9907714,0.005971757,0.001311984,0.00101866,0.000007124925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2459101,0.0004080462,0.7094042,0.0003013549,0.0002477211,0.0002782209,0.001326112,0.03770065,0.004423725],"genre_scores_gemma":[0.6840544,0.0001651806,0.303886,0.0001990213,0.00005089198,0.0001461074,0.003769334,0.001024514,0.006704621],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005421382,"threshold_uncertainty_score":0.01077962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0476470463432403,"score_gpt":0.1670380667585388,"score_spread":0.1193910204152985,"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."}}