{"id":"W4412369264","doi":"10.3390/rs17142337","title":"CSDNet: Context-Aware Segmentation of Disaster Aerial Imagery Using Detection-Guided Features and Lightweight Transformers","year":2025,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec en Outaouais","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Computer science; Artificial intelligence; Transformer; Image segmentation; Context (archaeology); Computer vision; Machine learning; Geography; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002701771,0.0006506231,0.0005037049,0.0009093384,0.0002908971,0.0007935234,0.00117391,0.000592193,0.001397804],"category_scores_gemma":[0.0007746133,0.0003179835,0.0006260579,0.0006484718,0.0003692514,0.001150684,0.00127949,0.0006378998,0.0005779567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007645896,"about_ca_system_score_gemma":0.0008116288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006401464,"about_ca_topic_score_gemma":0.01435185,"domain_scores_codex":[0.9998249,0.00001440943,0.000009140771,0.0000744592,0.00004964041,0.00002749867],"domain_scores_gemma":[0.9998766,0.00002751504,0.00001530164,0.00002769152,0.00003595195,0.00001689604],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006243556,0.0002396113,0.004209916,0.0002517293,0.0001270653,0.0002370598,0.0002326304,0.2405972,0.09586707,0.007883217,0.01151787,0.6382123],"study_design_scores_gemma":[0.00001508316,0.00004746717,0.001023605,0.00001047141,0.00001914817,0.0001006579,0.00003534916,0.9742735,0.0170549,0.003565622,0.003841144,0.00001299131],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03543857,0.0003266205,0.9564652,0.0001127804,0.00006689503,0.0001170643,0.000553327,0.005429904,0.001489685],"genre_scores_gemma":[0.5340226,0.0003597257,0.4593756,0.0001865373,0.00005938925,0.0001689532,0.002281437,0.0004720264,0.003073569],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006401464,"threshold_uncertainty_score":0.01272839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01404815280905266,"score_gpt":0.2507789296657732,"score_spread":0.2367307768567205,"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."}}