{"id":"W3088134661","doi":"10.1109/access.2020.3026658","title":"VNet: An End-to-End Fully Convolutional Neural Network for Road Extraction From High-Resolution Remote Sensing Data","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":188,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Centre for Advanced Modelling and Geospatial lnformation Systems, University of Technology Sydney; King Saud University; University of Technology Sydney","keywords":"Computer science; Segmentation; Deep learning; Artificial intelligence; Cross entropy; Convolutional neural network; Entropy (arrow of time); Image segmentation; High resolution; Pattern recognition (psychology); Remote sensing; Computer vision; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001583024,0.0002110303,0.0002095681,0.00005867656,0.0002070155,0.0002147094,0.0004214926,0.0001581526,0.00005830147],"category_scores_gemma":[0.0000467983,0.0002331284,0.00004402213,0.0002629059,0.0000199956,0.00156983,0.00006917054,0.0002509545,0.00003354281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009428438,"about_ca_system_score_gemma":0.00002701971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00110611,"about_ca_topic_score_gemma":0.0002474712,"domain_scores_codex":[0.9985671,0.00004333367,0.0003116477,0.0004778646,0.0002332164,0.0003668475],"domain_scores_gemma":[0.9991821,0.0000912498,0.00009060751,0.0003920218,0.0000651247,0.0001789018],"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":[0.0001219603,0.00001066816,0.00005323535,0.0000285553,0.00005815062,0.000009806459,0.00006104156,0.7823475,0.05458677,0.00001368857,0.02056842,0.1421402],"study_design_scores_gemma":[0.0003514033,0.00004453068,0.01124055,0.00003570234,0.00006031297,0.00001063656,0.0000128046,0.9757974,0.002969085,0.000208225,0.008995437,0.0002739393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4816825,0.0001268613,0.5136626,0.0004864004,0.002687002,0.0002615961,0.0002930106,0.0007541036,0.00004592452],"genre_scores_gemma":[0.973079,0.00001880286,0.02079215,0.0003573814,0.004224092,0.000002369489,0.001456397,0.00005957134,0.00001020014],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4928705,"threshold_uncertainty_score":0.9506699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0653926588942447,"score_gpt":0.3114334813044918,"score_spread":0.2460408224102471,"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."}}