{"id":"W4388191449","doi":"10.1145/3581783.3611738","title":"SemanticRT: A Large-Scale Dataset and Method for Robust Semantic Segmentation in Multispectral Images","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Multispectral image; Computer science; Artificial intelligence; Segmentation; Scale (ratio); Image segmentation; Pattern recognition (psychology); Computer vision; Cartography; Geography","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":[0.0002910903,0.00009498778,0.0001158848,0.0001142195,0.0001057823,0.00006770873,0.0002541858,0.00002630115,0.000004306864],"category_scores_gemma":[0.00001953228,0.0000896537,0.00001898814,0.0006124881,0.00001625165,0.0004322944,0.0001971841,0.0000607785,0.00002100414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001203227,"about_ca_system_score_gemma":0.000008562741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002242344,"about_ca_topic_score_gemma":0.0002821576,"domain_scores_codex":[0.9989975,0.00003634616,0.0001716799,0.0004116903,0.00009022935,0.0002925564],"domain_scores_gemma":[0.9992856,0.0002926812,0.00004254501,0.0003111335,0.0000176922,0.00005029391],"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":[0.00008048688,0.001033581,0.01673711,0.0006506741,0.000129826,0.0001582646,0.005690789,0.1387276,0.2599972,0.1433897,0.2134839,0.2199209],"study_design_scores_gemma":[0.0006207,0.00002518533,0.005022218,0.000007969098,0.000007327217,0.00001206058,0.00009397484,0.9808841,0.00828308,0.00417592,0.0007349076,0.0001325924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003704431,0.00002245483,0.9934334,0.001862618,0.00004273952,0.0005345549,0.0001824312,0.0001915489,0.00002584679],"genre_scores_gemma":[0.01103987,0.00005453801,0.9877872,0.0002814811,0.00002746003,0.0001900462,0.0003887173,0.00001025238,0.0002203755],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8421564,"threshold_uncertainty_score":0.3655972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02850627719749593,"score_gpt":0.3390385355472103,"score_spread":0.3105322583497143,"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."}}