{"id":"W4402122272","doi":"10.1016/j.rsase.2024.101336","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":"article","venue":"Remote Sensing Applications Society and Environment","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Change detection; Block (permutation group theory); Sensitivity (control systems); Residual; Remote sensing; Process (computing); Net (polyhedron); Artificial intelligence; Data mining; Real-time computing; Geography; Engineering; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007786303,0.0004652573,0.0003304172,0.000310186,0.0005174843,0.0003650459,0.0001031911,0.0002979959,0.000001235393],"category_scores_gemma":[0.00002119987,0.000578174,0.0001293355,0.0007452547,0.0001217011,0.0004002262,0.00008470505,0.0004928448,0.00001631411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001181456,"about_ca_system_score_gemma":0.00002840345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006314326,"about_ca_topic_score_gemma":0.00005806582,"domain_scores_codex":[0.9971963,0.00009424362,0.0006631791,0.001070578,0.0003962947,0.0005794219],"domain_scores_gemma":[0.9988248,0.0001226428,0.0001267266,0.0007074152,0.00004368614,0.000174667],"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":[0.000003561506,0.000009390289,0.000001271634,0.0001056321,0.00001670478,0.000002008655,0.0002807676,0.07545278,0.5204617,0.000009100559,0.000008110019,0.4036489],"study_design_scores_gemma":[0.0002672062,0.00002313772,0.0003481999,0.0003536249,0.00008854248,0.0000908001,0.0002442124,0.9432446,0.05120388,0.0002466857,0.003349522,0.0005395307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2265338,0.000428197,0.7708887,0.0004945967,0.0001155795,0.001005144,0.00002128894,0.0004950878,0.00001756142],"genre_scores_gemma":[0.4545388,0.0001126619,0.5446853,0.0001120922,0.0003551132,0.000002379889,0.00007693582,0.000109102,0.000007639142],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8677919,"threshold_uncertainty_score":0.999667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02455593584750891,"score_gpt":0.2560075147596258,"score_spread":0.2314515789121169,"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."}}