{"id":"W3121754326","doi":"10.1109/jstars.2021.3053603","title":"Reconstruction Bias U-Net for Road Extraction From Optical Remote Sensing Images","year":2021,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":106,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Decoding methods; Segmentation; Remote sensing; Information extraction; Feature extraction; Deep learning; Image segmentation; Computer vision; Intelligent transportation system; Pattern recognition (psychology); Geography; Telecommunications","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":[0.0006124878,0.001793095,0.0009871883,0.001942331,0.0006535283,0.0009467752,0.002138061,0.001544616,0.00353854],"category_scores_gemma":[0.001327702,0.0005448633,0.001286468,0.001429074,0.0005419086,0.001772775,0.001155713,0.001573527,0.002747531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009815519,"about_ca_system_score_gemma":0.001368279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01007089,"about_ca_topic_score_gemma":0.02408744,"domain_scores_codex":[0.9994815,0.00004617314,0.00002926706,0.0002184415,0.0001332411,0.00009135859],"domain_scores_gemma":[0.9996527,0.00006032135,0.00004755521,0.0001207583,0.00009704944,0.00002156561],"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":[0.0005880655,0.0003266841,0.005074884,0.0003412338,0.0001881484,0.0002564063,0.00008799939,0.1391988,0.02392645,0.005174091,0.02340093,0.8014364],"study_design_scores_gemma":[0.000026438,0.00008374491,0.001805353,0.00003779964,0.0000571173,0.0001571531,0.00005711762,0.9550273,0.03029429,0.004345346,0.008076171,0.00003226309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.104172,0.002151599,0.8540484,0.0005279996,0.000364515,0.0003780144,0.004096565,0.02392028,0.01034074],"genre_scores_gemma":[0.4351955,0.0008973122,0.5268976,0.0005945496,0.0001823679,0.0003412393,0.0187099,0.001125299,0.01605624],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01007089,"threshold_uncertainty_score":0.02002454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0286536655783256,"score_gpt":0.2456760576844232,"score_spread":0.2170223921060976,"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."}}