{"id":"W2547880720","doi":"10.1109/igarss.2016.7729406","title":"Fully convolutional networks for building and road extraction: Preliminary results","year":2016,"lang":"en","type":"article","venue":"","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":190,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Pooling; Segmentation; Deep learning; Context (archaeology); Artificial intelligence; Image segmentation; Field (mathematics); Computation; Filter (signal processing); Convolutional neural network; Machine learning; Pattern recognition (psychology); Computer vision; Algorithm","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":[0.0001401629,0.0001048429,0.00008696307,0.00005038693,0.00009348269,0.000023242,0.00004142623,0.0001106035,0.0000292701],"category_scores_gemma":[0.00003514402,0.00007545149,0.00003275435,0.00005092731,0.00002436228,0.0002789321,0.00001198205,0.00006158745,0.000006938505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005054611,"about_ca_system_score_gemma":0.000006977907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004347148,"about_ca_topic_score_gemma":0.000001737703,"domain_scores_codex":[0.9993856,0.000006714831,0.0001813213,0.0001643808,0.00006896679,0.0001930427],"domain_scores_gemma":[0.9996346,0.0001573455,0.00003021509,0.00008933071,0.00003426359,0.00005423111],"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":[0.0011926,0.00007508343,0.0003410958,0.0001268522,0.0001895623,0.00001207869,0.00006880944,0.08805084,0.1670145,0.01059713,0.1228331,0.6094984],"study_design_scores_gemma":[0.002157473,0.0002809096,0.02756112,0.0001799679,0.0000417627,0.0001747849,0.00003015273,0.8850179,0.00778221,0.0006646065,0.07565989,0.0004491929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1468409,0.0006437905,0.8464462,0.0005979501,0.001180097,0.0002593544,0.00002540758,0.001168905,0.00283741],"genre_scores_gemma":[0.9917063,0.000141946,0.006671515,0.0000181081,0.0003859474,0.00002870784,0.000007910878,0.0000207011,0.001018922],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8448653,"threshold_uncertainty_score":0.3076823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01013052199863083,"score_gpt":0.2382695766086522,"score_spread":0.2281390546100214,"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."}}