{"id":"W3158435984","doi":"10.48550/arxiv.2104.12300","title":"ODDObjects: A Framework for Multiclass Unsupervised Anomaly Detection on Masked Objects","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Autoencoder; Anomaly detection; Artificial intelligence; Computer science; Pattern recognition (psychology); Anomaly (physics); Convolutional neural network; Object (grammar); Unsupervised learning; Deep learning","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":[0.0008101522,0.001158471,0.001071493,0.001752685,0.0004439123,0.001063389,0.002067155,0.0009179648,0.001538437],"category_scores_gemma":[0.00191809,0.0004908543,0.001166664,0.0008178958,0.0008048356,0.00158601,0.00200679,0.001477463,0.0007744483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007259616,"about_ca_system_score_gemma":0.001023224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005596672,"about_ca_topic_score_gemma":0.008441718,"domain_scores_codex":[0.9993808,0.00008725635,0.00002884597,0.00023073,0.0001772163,0.00009500845],"domain_scores_gemma":[0.9993105,0.0001641214,0.0001201792,0.0002013665,0.0001429113,0.00006081429],"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":[0.0005680188,0.0002584503,0.01375668,0.0002503862,0.0003959704,0.0006103857,0.0003400183,0.1363257,0.06482119,0.02335236,0.01560467,0.7437163],"study_design_scores_gemma":[0.00001130152,0.00006265118,0.001801849,0.00001639907,0.00002292272,0.0002734039,0.00003560981,0.9601364,0.01767604,0.0140767,0.005860366,0.00002633542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0169095,0.0002278051,0.9752566,0.00008615255,0.00004358896,0.00005704581,0.0004000841,0.006336889,0.0006823787],"genre_scores_gemma":[0.2562574,0.00028878,0.7359718,0.0001648105,0.00008359997,0.0001416184,0.00262448,0.0009329315,0.003534516],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005596672,"threshold_uncertainty_score":0.01112819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06926371866493562,"score_gpt":0.2076288915838352,"score_spread":0.1383651729188995,"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."}}