{"id":"W4402262800","doi":"10.1109/igarss53475.2024.10641520","title":"UnderstAnding Bag of Tricks of Deep Learning-Based Semantic Segmentation in Pavement Crack Detection","year":2024,"lang":"en","type":"article","venue":"","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Deep learning; Image segmentation; Computer vision; Natural language processing","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":[0.0020441,0.0008915922,0.0008026498,0.001030591,0.0004340819,0.001645027,0.001550628,0.00128104,0.001885963],"category_scores_gemma":[0.00701068,0.0006038061,0.0005597657,0.0007947088,0.001189089,0.004126229,0.002040619,0.00246159,0.0005764125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008284469,"about_ca_system_score_gemma":0.0009630009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004166201,"about_ca_topic_score_gemma":0.005514222,"domain_scores_codex":[0.9994872,0.0001381293,0.00003183768,0.0001652635,0.0001093431,0.00006820773],"domain_scores_gemma":[0.9978805,0.001195022,0.000223096,0.0003608736,0.0002437377,0.00009686242],"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":[0.0003673282,0.000205964,0.006484921,0.0002342299,0.00009042961,0.0002036612,0.0002892307,0.5450243,0.01325114,0.05723598,0.006506069,0.3701067],"study_design_scores_gemma":[0.000004476305,0.0000209928,0.000374394,0.00001098834,0.000005830624,0.00002854348,0.00001218667,0.979926,0.001647576,0.01736981,0.0005934922,0.000005700937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05636057,0.0007133373,0.9387739,0.0008183154,0.00007667785,0.00005090656,0.0001756168,0.001200885,0.001829732],"genre_scores_gemma":[0.7379468,0.0007138438,0.2569177,0.0004540021,0.0001222621,0.000134099,0.0006716521,0.0002722515,0.00276729],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004166201,"threshold_uncertainty_score":0.01081032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01874564306517288,"score_gpt":0.231089385329483,"score_spread":0.2123437422643102,"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."}}