{"id":"W3158580822","doi":"10.1016/j.jag.2021.102341","title":"Adaboost-like End-to-End multiple lightweight U-nets for road extraction from optical remote sensing images","year":2021,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Key Technologies Research and Development Program; Science and Technology Major Project of Guangxi; Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"AdaBoost; Segmentation; Artificial intelligence; Computer science; Deep learning; Machine learning; Data mining; Pattern recognition (psychology); Support vector machine","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":[0.0002126092,0.0001382481,0.0001671161,0.0001891602,0.00008089219,0.0001981936,0.0000812268,0.0001087008,0.00004723829],"category_scores_gemma":[0.00008976944,0.0001379486,0.00006964419,0.0001154255,0.00001277554,0.0009555903,0.00001932933,0.0001807928,0.00001832285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006934912,"about_ca_system_score_gemma":0.00004189877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001745564,"about_ca_topic_score_gemma":0.00002374325,"domain_scores_codex":[0.9987611,0.000008479717,0.0005947283,0.000107701,0.0003901391,0.0001378329],"domain_scores_gemma":[0.9989194,0.0001347868,0.0002395631,0.0000803542,0.00054699,0.00007887518],"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":[0.000193684,0.00001766042,0.00004506249,0.00002381836,0.0001350012,0.000009376331,0.0005313205,0.04017242,0.1325945,0.0002077531,0.001179701,0.8248897],"study_design_scores_gemma":[0.001603542,0.0000454646,0.04344227,0.0001475726,0.00005249753,0.0001452125,0.0003416072,0.6193062,0.2124557,0.000797633,0.1213819,0.000280383],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5854454,0.00009291973,0.410409,0.0008900207,0.00173088,0.00016854,0.00004096511,0.0001028875,0.001119374],"genre_scores_gemma":[0.9012821,0.0001587929,0.09731109,0.0004624245,0.0003927958,0.000001322484,0.0003058432,0.00001821095,0.00006737057],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8246093,"threshold_uncertainty_score":0.5625381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01228173746527353,"score_gpt":0.23666392197992,"score_spread":0.2243821845146465,"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."}}