{"id":"W4362600044","doi":"10.1111/mice.13001","title":"Unsupervised defect segmentation with pose priors","year":2023,"lang":"en","type":"article","venue":"Computer-Aided Civil and Infrastructure Engineering","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Leverage (statistics); Segmentation; Outlier; Minimum bounding box; False alarm; Bounding overwatch; Computer vision; Pattern recognition (psychology); Machine learning; Image (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":[0.0001159371,0.0002557933,0.0002395874,0.0002802357,0.00008473913,0.0001058522,0.000078993,0.0001342577,0.00002017906],"category_scores_gemma":[0.000008709493,0.0002188118,0.00005866036,0.0005903234,0.0000129599,0.0002107539,0.00003692027,0.0002363965,0.00001659343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005411499,"about_ca_system_score_gemma":0.0000108572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000572135,"about_ca_topic_score_gemma":0.000002793869,"domain_scores_codex":[0.9990456,0.00001572394,0.0002332057,0.0002307788,0.0001754013,0.0002992552],"domain_scores_gemma":[0.9996017,0.00005565036,0.00002790654,0.0001685172,0.0000321609,0.0001140274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001301077,0.000002466471,0.0006279502,0.0001878216,0.00009545784,0.00002128095,0.0005059767,0.9368017,0.02896519,0.0000747324,0.001792146,0.0309123],"study_design_scores_gemma":[0.001431368,0.0002615027,0.04964737,0.0002407142,0.00003852061,0.000138289,0.0001140847,0.9350919,0.006288802,0.00005329004,0.006089052,0.0006050729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8546883,0.0001140079,0.1422721,0.000007438522,0.001202461,0.0002329898,0.000006276456,0.001279834,0.0001966283],"genre_scores_gemma":[0.9972423,0.00003614367,0.002007896,0.00001721597,0.0005840588,0.00002023614,0.00002214186,0.00005683085,0.0000131673],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.142554,"threshold_uncertainty_score":0.8922888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004417954318021914,"score_gpt":0.1704507330625819,"score_spread":0.16603277874456,"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."}}