{"id":"W4402260084","doi":"10.1109/igarss53475.2024.10640473","title":"CornerRegNet: Building Segmentation from Overhead Imagery Using Oriented Corners in Deep Networks","year":2024,"lang":"en","type":"article","venue":"","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Overhead (engineering); Segmentation; Artificial intelligence; Image segmentation; Computer vision; Pattern recognition (psychology)","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":[0.00009178659,0.0001506535,0.000127184,0.0001790936,0.00003686901,0.0001034296,0.00004899397,0.0001105467,0.0001563472],"category_scores_gemma":[0.000006858739,0.0001490684,0.00004257279,0.0004343906,0.00001404468,0.0004274517,0.00001517713,0.0002250932,0.00001951891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002659562,"about_ca_system_score_gemma":0.00001134771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000298002,"about_ca_topic_score_gemma":0.00006019101,"domain_scores_codex":[0.9991801,0.00001691352,0.0002366188,0.0002165174,0.0001112057,0.0002386556],"domain_scores_gemma":[0.999757,0.00007429827,0.00001812154,0.00009737534,0.00001055868,0.00004268314],"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":[0.000006710651,0.00001054283,0.001140319,0.00002715951,0.0000399567,0.0000502687,0.0001606351,0.8710527,0.1040889,0.000181232,0.0006813007,0.0225602],"study_design_scores_gemma":[0.0001542616,0.000005830348,0.00171855,0.0001917147,0.00002130574,0.000009171957,0.0001438628,0.9920776,0.005094618,0.00006753399,0.0003357507,0.0001798142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5709981,0.001075752,0.4250088,0.000006355498,0.001451527,0.00007875827,0.000002229892,0.0008593922,0.0005191474],"genre_scores_gemma":[0.9909484,0.00009588877,0.008591049,0.00002431137,0.0001976789,0.00000683394,0.00005243919,0.00004628693,0.00003706788],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4199504,"threshold_uncertainty_score":0.6078834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00963523418789727,"score_gpt":0.2476158081763446,"score_spread":0.2379805739884473,"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."}}