{"id":"W3159395695","doi":"10.1139/cjce-2020-0764","title":"Detecting potholes in asphalt pavement under small-sample conditions based on improved faster region-based convolution neural networks","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pothole (geology); Computer science; Convolutional neural network; Convolution (computer science); Artificial intelligence; Pattern recognition (psychology); Object detection; Frame (networking); Feature (linguistics); Feature extraction; Sample (material); Set (abstract data type); Artificial neural network; Computer vision; Geology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001455896,0.0001926052,0.0002206229,0.000393138,0.00007325812,0.0000695076,0.0001074485,0.0001006601,0.000039237],"category_scores_gemma":[0.0001189894,0.0002129765,0.0001017918,0.0002645869,0.00001745404,0.0001025157,0.000004557499,0.0005088227,4.061647e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005400977,"about_ca_system_score_gemma":0.00025703,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002958539,"about_ca_topic_score_gemma":0.04418588,"domain_scores_codex":[0.9989058,0.00002224981,0.0003722449,0.0001201702,0.00009617772,0.0004832924],"domain_scores_gemma":[0.9992294,0.0001505666,0.00006834288,0.000148741,0.0001177114,0.0002852632],"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":[0.000003289087,0.000003017133,0.001527243,0.00004081409,0.00001914675,0.0001911064,0.0000493888,0.9956189,0.001964005,0.00005126355,0.00004514337,0.0004867101],"study_design_scores_gemma":[0.0006518055,0.00004174813,0.007568723,0.0003952427,0.00001751628,0.00004406326,0.0001344392,0.9881849,0.002375806,0.00003489918,0.0003345731,0.0002162921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1727723,0.0004758936,0.8236633,0.0001866993,0.002573719,0.0001186561,0.00001467839,0.00005276435,0.0001420025],"genre_scores_gemma":[0.9985224,0.000003688609,0.000861925,0.0001998593,0.0003440567,0.000007051377,0.00001078277,0.00004580715,0.000004423209],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8257501,"threshold_uncertainty_score":0.9732552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009384446653444583,"score_gpt":0.1844962669776172,"score_spread":0.1751118203241726,"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."}}