{"id":"W4404789475","doi":"10.1016/j.procir.2024.10.320","title":"Anomaly detection on MVTec AD using VQ-VAE-2","year":2024,"lang":"en","type":"article","venue":"Procedia CIRP","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Investment Agriculture Foundation; Agency for Science, Technology and Research","keywords":"Anomaly detection; Anomaly (physics); Pattern recognition (psychology); Artificial intelligence; Geology; Computer science; Mathematics; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001107503,0.0001202678,0.00008525446,0.0001802502,0.0001819709,0.0002474069,0.0003260259,0.00007587198,0.00001427422],"category_scores_gemma":[0.00001614014,0.0001148366,0.00007085263,0.0006849649,0.00002411031,0.0003397585,0.00007880604,0.0001773047,0.0001881109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009209255,"about_ca_system_score_gemma":0.00006655588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002065017,"about_ca_topic_score_gemma":0.000007133352,"domain_scores_codex":[0.9990425,0.00001151824,0.0001584404,0.0004292897,0.0001637937,0.0001945278],"domain_scores_gemma":[0.9994808,0.00003321244,0.00003930435,0.0003292022,0.00005090647,0.00006651634],"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":[0.000007108571,0.00008138552,0.00008016444,0.00008967676,0.00002994939,0.00001675955,0.0003946725,0.0000789093,0.08781805,0.04000885,0.0009713673,0.8704231],"study_design_scores_gemma":[0.0001283752,0.0003013898,0.0009689502,0.0001098464,0.00002825735,0.0001769487,0.00002774125,0.4649724,0.411852,0.01806934,0.10285,0.0005147121],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03774501,0.000237501,0.9568553,0.0004549335,0.0004065573,0.0002259159,0.000002190302,0.001505823,0.002566762],"genre_scores_gemma":[0.9828044,0.00002855078,0.01635675,0.000161364,0.00018237,0.0001014764,7.332172e-7,0.00001645341,0.000347926],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9450594,"threshold_uncertainty_score":0.4682902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02032027952199756,"score_gpt":0.2748372726133923,"score_spread":0.2545169930913947,"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."}}