{"id":"W4400942153","doi":"10.2139/ssrn.4904751","title":"Building Detection in Vhr Remote Sensing Images Using a Novel Dual Attention Residual-Based U-Net (Dattresu-Net): An Application to Generating Building Change Maps","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Net (polyhedron); Change detection; Residual; Remote sensing; Computer science; Dual (grammatical number); Artificial intelligence; Computer vision; Geography; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003446256,0.0006812389,0.0005312944,0.001443097,0.0002780707,0.0004979111,0.0009312907,0.000600688,0.002984572],"category_scores_gemma":[0.0004623375,0.0002492342,0.0005574782,0.0009232456,0.0002175477,0.0004109755,0.0007203337,0.000346621,0.001077596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003467484,"about_ca_system_score_gemma":0.000420991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007785283,"about_ca_topic_score_gemma":0.01596676,"domain_scores_codex":[0.9998664,0.00001374299,0.000005612141,0.00004816315,0.0000407908,0.00002532672],"domain_scores_gemma":[0.9998261,0.00004445892,0.00001820339,0.00002650571,0.00006854679,0.00001619367],"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":[0.0004045053,0.0002091308,0.003185795,0.0001410212,0.00008058742,0.0001264059,0.00005840459,0.0533016,0.05282054,0.001001971,0.004636179,0.8840338],"study_design_scores_gemma":[0.00001465001,0.00007569067,0.004088682,0.000008791728,0.00003925866,0.00008026031,0.00003085353,0.9646186,0.02871679,0.0007038362,0.001610173,0.00001241297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1763107,0.0004492693,0.8036695,0.0002012227,0.00015161,0.0001512535,0.001643461,0.01217849,0.005244564],"genre_scores_gemma":[0.4931364,0.0002197677,0.4971857,0.0001198793,0.00008426096,0.0001022497,0.002816754,0.0003512963,0.005983724],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007785283,"threshold_uncertainty_score":0.01547992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0262046157568455,"score_gpt":0.2849646454146078,"score_spread":0.2587600296577623,"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."}}