{"id":"W4320518953","doi":"10.1016/j.autcon.2023.104771","title":"Hybrid DNN training using both synthetic and real construction images to overcome training data shortage","year":2023,"lang":"en","type":"article","venue":"Automation in Construction","topic":"3D Surveying and Cultural Heritage","field":"Earth and Planetary Sciences","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Economic shortage; Artificial intelligence; Training (meteorology); Field (mathematics); Computer science; Automation; Artificial neural network; Synthetic data; Training set; Machine learning; Engineering","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":[0.0009458375,0.001116111,0.0005194286,0.0008418782,0.0003996798,0.0005409569,0.0008832971,0.0009617991,0.002603542],"category_scores_gemma":[0.00154699,0.0004230116,0.0005711945,0.0009024428,0.000340537,0.0010216,0.0006427909,0.0009441741,0.001095827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004523046,"about_ca_system_score_gemma":0.0007987353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01549894,"about_ca_topic_score_gemma":0.01983552,"domain_scores_codex":[0.9995767,0.00006561394,0.00002824317,0.0001517561,0.00009244774,0.00008513672],"domain_scores_gemma":[0.9993603,0.0001985167,0.00002071815,0.0001249834,0.0002717224,0.00002383072],"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":[0.0005501938,0.0003384929,0.005743518,0.0002202985,0.0001535197,0.0003150675,0.0001146146,0.1928321,0.04541854,0.001054448,0.008952373,0.7443068],"study_design_scores_gemma":[0.00002184422,0.00007760359,0.002935121,0.00003247803,0.00007865761,0.00008875736,0.00006729225,0.9678966,0.02464932,0.0007335063,0.003403233,0.00001547714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4362774,0.001952302,0.5311621,0.000459481,0.0007292416,0.0001900968,0.001824253,0.007452244,0.01995278],"genre_scores_gemma":[0.8450335,0.000387722,0.1421065,0.0003363239,0.00006193638,0.00009526152,0.004608185,0.0002412939,0.00712916],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01549894,"threshold_uncertainty_score":0.03081745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09673258083927715,"score_gpt":0.2900833869106985,"score_spread":0.1933508060714214,"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."}}