{"id":"W3203407718","doi":"10.1109/jstars.2021.3116062","title":"PSRN: Polarimetric Space Reconstruction Network for PolSAR Image Semantic Segmentation","year":2021,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Synthetic Aperture Radar (SAR) Applications and Techniques","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Space Agency; Jet Propulsion Laboratory; National Natural Science Foundation of China; National Aeronautics and Space Administration; China Aerospace Science and Technology Corporation; Deutsches Zentrum für Luft- und Raumfahrt; National Science Foundation","keywords":"Polarimetry; Computer science; Artificial intelligence; Pattern recognition (psychology); Convolutional neural network; Remote sensing; Scattering; Segmentation; Feature vector; Image segmentation; Feature (linguistics); Feature extraction; Computer vision; Geography; Physics; Optics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002227348,0.0001212388,0.0002231222,0.0001799888,0.0001181633,0.00005859835,0.00004221149,0.0001148135,0.00000265335],"category_scores_gemma":[0.00006068566,0.0001235642,0.00004416477,0.0009076414,0.0000272484,0.00008842952,0.000006649887,0.0002459032,2.351498e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006634147,"about_ca_system_score_gemma":0.00007469398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002128389,"about_ca_topic_score_gemma":0.00007671348,"domain_scores_codex":[0.9991223,0.00002163352,0.000420376,0.0001238159,0.0001302184,0.0001816982],"domain_scores_gemma":[0.9992205,0.000124221,0.0001381434,0.000116944,0.0003542998,0.00004590695],"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":[0.000008979478,0.00001214159,0.000132095,0.00006104943,0.00005263005,0.00000496753,0.00009359687,0.0004288456,0.0793371,0.0007655167,0.0002814447,0.9188216],"study_design_scores_gemma":[0.002247094,0.0001325757,0.0279955,0.0007557857,0.0002981464,0.001729766,0.0006646797,0.4167401,0.4024317,0.03643465,0.1096486,0.0009214239],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1223631,0.0004327209,0.8759109,0.0004225099,0.0002694677,0.0002066571,0.000004113646,0.00005154177,0.0003389906],"genre_scores_gemma":[0.07828153,0.0006104445,0.9206137,0.00004971441,0.0003850846,2.317892e-7,0.000009528821,0.00002188332,0.0000278982],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9179002,"threshold_uncertainty_score":0.5038801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01391894756618631,"score_gpt":0.2260200673213312,"score_spread":0.2121011197551449,"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."}}