{"id":"W4387789981","doi":"10.1109/tiv.2023.3326136","title":"Pavement Defect Detection With Deep Learning: A Comprehensive Survey","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Vehicles","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"China Postdoctoral Science Foundation","keywords":"Robustness (evolution); Computer science; Adaptability; Artificial intelligence; Deep learning; Field (mathematics); Machine learning; Key (lock); Data mining","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001194111,0.0002181711,0.000168062,0.0002444427,0.0002107065,0.00004373282,0.00009291282,0.00008228274,0.00003579894],"category_scores_gemma":[0.000002895157,0.0001925724,0.000100717,0.0004919195,0.00003989244,0.00007929579,0.000001042755,0.0003997311,0.0002376444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001292718,"about_ca_system_score_gemma":0.000008222279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009426208,"about_ca_topic_score_gemma":0.0004981715,"domain_scores_codex":[0.9989634,0.00006048081,0.0001968122,0.0002177163,0.0002117858,0.0003498343],"domain_scores_gemma":[0.9994859,0.000153165,0.00002602048,0.0001684036,0.00009101345,0.00007553935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007375958,0.0000169166,0.0004458333,0.00004006847,0.0001535632,0.00001078653,0.0004422831,0.8949118,0.01613579,0.000002624443,0.00002901773,0.08773754],"study_design_scores_gemma":[0.0003579136,0.0004641847,0.01438114,0.00009962764,0.00005728526,0.00001715264,0.00103961,0.07519633,0.9049124,0.00004447137,0.002975266,0.0004545822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5341629,0.00003261692,0.4642247,0.000003894007,0.0007284487,0.0001440533,0.000006225809,0.0006271929,0.00006995126],"genre_scores_gemma":[0.9992024,0.0003168296,0.0001119175,0.00001713664,0.00006395023,0.0000750781,0.000007195978,0.00005759629,0.0001479511],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8887767,"threshold_uncertainty_score":0.7852876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02053928644184242,"score_gpt":0.2332616647149851,"score_spread":0.2127223782731426,"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."}}