{"id":"W3153261712","doi":"10.3390/rs13081472","title":"Uncertainty Estimation for Deep Learning-Based Segmentation of Roads in Synthetic Aperture Radar Imagery","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University","keywords":"Softmax function; Computer science; Artificial intelligence; Synthetic aperture radar; Segmentation; Machine learning; Deep learning; Radar; Dropout (neural networks); Image segmentation; Data mining","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001293335,0.00009122195,0.0001382288,0.00009224846,0.00004122814,0.00001819575,0.00001789796,0.00008232227,0.00000462434],"category_scores_gemma":[0.0002085364,0.00009945087,0.00005052251,0.0001814602,0.00001113766,0.00007724969,0.000003854464,0.0001195318,0.000001997382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001196325,"about_ca_system_score_gemma":0.00002225899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000020016,"about_ca_topic_score_gemma":0.00001694004,"domain_scores_codex":[0.9994195,0.0000381516,0.0001964178,0.0001213143,0.00009455899,0.0001301141],"domain_scores_gemma":[0.9995932,0.0001939456,0.00005319426,0.00008516552,0.00005584187,0.00001866072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006295004,0.000003770959,0.000002943912,0.0001009895,0.000005718837,0.000004978379,0.00007446473,0.5910415,0.2251004,0.000001125716,0.000007999515,0.1836498],"study_design_scores_gemma":[0.0002602627,0.00001002268,0.0001150445,0.0002011354,0.00001583412,0.00001468372,0.00009976522,0.8900362,0.108933,0.00006244922,0.0001619851,0.00008959736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.319878,0.0001644423,0.6793762,0.00006749306,0.0001502486,0.00009845958,0.000001198464,0.0001565017,0.0001073879],"genre_scores_gemma":[0.9122536,0.00001703396,0.08757402,0.00001994829,0.00002518549,5.114811e-8,0.00007321632,0.00002352125,0.00001341676],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5923756,"threshold_uncertainty_score":0.4055489,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007052204189798283,"score_gpt":0.2336767110310574,"score_spread":0.2266245068412591,"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."}}