{"id":"W4414397831","doi":"10.3389/frsen.2025.1680450","title":"ConvAttentionNet: a high-performance model for efficient and accurate PolSAR data classification","year":2025,"lang":"en","type":"article","venue":"Frontiers in Remote Sensing","topic":"Synthetic Aperture Radar (SAR) Applications and Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Synthetic aperture radar; Pattern recognition (psychology); Classifier (UML); Convolutional neural network; Convolution (computer science); Benchmark (surveying); Preprocessor; Contextual image classification; Wavelet; Data modeling","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":[],"consensus_categories":[],"category_scores_codex":[0.0001780215,0.0001117259,0.000150441,0.0001517685,0.00007825323,0.00002951451,0.0001320529,0.0000835666,2.564567e-7],"category_scores_gemma":[0.00002620186,0.0001160241,0.00001405774,0.0001822997,0.00004461868,0.00006466288,0.00004194344,0.0000919774,4.074817e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007898889,"about_ca_system_score_gemma":0.00001889717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001423249,"about_ca_topic_score_gemma":0.000004774785,"domain_scores_codex":[0.9993132,0.000008795144,0.0002084141,0.0002479411,0.00005883473,0.0001627572],"domain_scores_gemma":[0.999433,0.00003424841,0.00003123993,0.0004483999,0.0000315388,0.00002161177],"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":[0.000008474971,0.000005451781,0.00003151245,0.00007581688,0.00001714592,1.985714e-7,0.00005209311,0.002532742,0.0005189839,0.0006670855,0.002871642,0.9932188],"study_design_scores_gemma":[0.0001993179,0.000003237581,0.0004493804,0.0001150103,0.00001945157,0.000001797796,0.00006584835,0.9837731,0.00157171,0.001473518,0.01221477,0.0001129189],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02565338,0.0004207116,0.9722509,0.000350253,0.0002465862,0.0003910846,0.00002184206,0.0001712138,0.0004940456],"genre_scores_gemma":[0.4574374,0.0001100189,0.5423117,0.00003480428,0.00001265327,5.569274e-7,0.00003995049,0.00001156652,0.00004135566],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9931059,"threshold_uncertainty_score":0.4731327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02249797032701499,"score_gpt":0.2559950471164152,"score_spread":0.2334970767894002,"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."}}