{"id":"W2945490722","doi":"10.48550/arxiv.1905.05889","title":"DARNet: Deep Active Ray Network for Building Segmentation","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; Nvidia","keywords":"Computer science; Artificial intelligence; Segmentation; Polygon (computer graphics); Convolutional neural network; Function (biology); Deep learning; Active contour model; Energy (signal processing); Computer vision; Intersection (aeronautics); Energy minimization; Image segmentation; Pattern recognition (psychology); Mathematics; Cartography; Frame (networking)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001367702,0.000303336,0.0002956938,0.0001189807,0.0002587601,0.00009126525,0.001578492,0.0002176158,0.000008259536],"category_scores_gemma":[0.00001687853,0.0003741151,0.0001937346,0.0006109803,0.00005587833,0.0005167861,0.00127939,0.0004093597,0.00004865275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003216051,"about_ca_system_score_gemma":0.0001003701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001256972,"about_ca_topic_score_gemma":0.00001665782,"domain_scores_codex":[0.9979432,0.00007802482,0.0001934457,0.001253875,0.0000793162,0.0004521872],"domain_scores_gemma":[0.9978074,0.0003601566,0.000402196,0.001152268,0.0001592757,0.0001186316],"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":[0.00002541794,0.00002124859,0.000187886,0.00002543103,0.00004609108,0.000005469139,0.00007101231,0.8524115,0.0001078131,0.1438238,0.0003704001,0.002903879],"study_design_scores_gemma":[0.0004158464,0.00003959751,0.0004072381,0.00004435567,0.0000521417,0.000001209078,0.00002676513,0.8682265,0.0003954407,0.1285832,0.001414443,0.000393205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02162591,0.00006220827,0.9754055,0.0001147001,0.0006856329,0.001295303,0.00001902697,0.0002692924,0.0005224516],"genre_scores_gemma":[0.8756638,0.0001171281,0.122963,0.000181691,0.0002627216,0.00001806596,0.00006734242,0.00002939021,0.0006968379],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8540379,"threshold_uncertainty_score":0.9998711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05916007232131909,"score_gpt":0.2228668598872059,"score_spread":0.1637067875658869,"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."}}