{"id":"W3111027253","doi":"10.1109/smc42975.2020.9283427","title":"Instance Segmentation of Personal Protective Equipment using a Multi-stage Transfer Learning Process","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Personal protective equipment; Computer science; Segmentation; Visibility; Process (computing); Transfer of learning; Artificial intelligence; Hazardous waste; Human–computer interaction; Engineering","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":[0.0008595031,0.001190325,0.00116033,0.001185845,0.0005047784,0.001215426,0.002344624,0.002507669,0.002595323],"category_scores_gemma":[0.00179004,0.0005261237,0.00158217,0.001093551,0.0005644323,0.00156215,0.001121711,0.001684662,0.001170965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001302822,"about_ca_system_score_gemma":0.00108212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009011154,"about_ca_topic_score_gemma":0.008845001,"domain_scores_codex":[0.9994068,0.00006574357,0.00002943262,0.0002941983,0.0001051186,0.0000987008],"domain_scores_gemma":[0.9994078,0.0002050471,0.00007259149,0.0001293697,0.0001415582,0.00004369221],"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":[0.0004425211,0.0002944099,0.00405188,0.000134864,0.000127266,0.0002051886,0.0001792504,0.3591357,0.03118697,0.002636894,0.004953063,0.596652],"study_design_scores_gemma":[0.000004835921,0.00003798295,0.0005378331,0.000004916209,0.00001047049,0.00002854183,0.00001561857,0.9920837,0.005590951,0.001283474,0.0003951476,0.000006569379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.110467,0.0003910237,0.8799776,0.0003312643,0.00007041129,0.0001507022,0.0003977394,0.005983334,0.002230789],"genre_scores_gemma":[0.6982031,0.0001818524,0.294254,0.0002968199,0.00006177965,0.0001623019,0.00168528,0.0002556109,0.004899255],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009011154,"threshold_uncertainty_score":0.01791739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09104418257880388,"score_gpt":0.3355138451696684,"score_spread":0.2444696625908646,"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."}}