{"id":"W4210874378","doi":"10.1109/lgrs.2022.3149709","title":"TAL: Topography-Aware Multi-Resolution Fusion Learning for Enhanced Building Footprint Extraction","year":2022,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Footprint; Computer science; Extraction (chemistry); Artificial intelligence; Fusion; Image resolution; Feature extraction; Computer vision; Resolution (logic); Sensor fusion; Remote sensing; Geology; Chemistry","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003278257,0.000157653,0.0001308095,0.0002414576,0.001079262,0.00007802367,0.00007608342,0.00005587389,0.00000176058],"category_scores_gemma":[0.00002017237,0.0001674165,0.00007589052,0.0003356183,0.00006322131,0.0001665475,0.00003259991,0.0003485731,8.365641e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001287754,"about_ca_system_score_gemma":0.000009370337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001260925,"about_ca_topic_score_gemma":0.000008706236,"domain_scores_codex":[0.9988458,0.00004187608,0.0001910873,0.0003342433,0.0002217143,0.0003652603],"domain_scores_gemma":[0.9996689,0.00005447305,0.000080576,0.0001109557,0.00002655078,0.00005854371],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007889824,0.000004363725,0.000004141612,0.00002088163,0.000004789906,0.000003619852,0.0001758887,0.1984855,0.6752832,0.000001164544,0.00004658163,0.125962],"study_design_scores_gemma":[0.0002750091,0.00004671267,0.0006743852,0.00005040148,0.00001487094,0.00007774552,0.0002670928,0.9407354,0.05456021,0.00001870701,0.003048433,0.0002310063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5034455,0.00003433823,0.4948046,0.0001348616,0.001154128,0.0001176712,9.288745e-7,0.0002990064,0.0000089431],"genre_scores_gemma":[0.9606281,0.00005325563,0.03897798,0.0001289054,0.0001313325,0.000001239199,0.000006230329,0.00002724667,0.00004572008],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.74225,"threshold_uncertainty_score":0.8300924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01229943828458877,"score_gpt":0.2456184134041989,"score_spread":0.2333189751196101,"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."}}