{"id":"W3100231084","doi":"10.1109/tgrs.2020.3033293","title":"Multigranularity Multiclass-Layer Markov Random Field Model for Semantic Segmentation of Remote Sensing Images","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"National Natural Science Foundation of China","keywords":"Computer science; Markov random field; Artificial intelligence; Segmentation; Image segmentation; Granularity; Pattern recognition (psychology); Pixel; Graph; Scale-space segmentation; Semantics (computer science); Computer vision; Theoretical computer science","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026432,0.000244262,0.0003163147,0.0001579629,0.000284711,0.00008214733,0.00007883405,0.0001343777,8.364677e-7],"category_scores_gemma":[0.00007634806,0.000247055,0.0001293841,0.0003321629,0.0001490997,0.0002735552,0.000002267351,0.0002584043,0.000003340449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004941702,"about_ca_system_score_gemma":0.00003295224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001820466,"about_ca_topic_score_gemma":0.00004921865,"domain_scores_codex":[0.9985205,0.0000494755,0.0004189728,0.0004272022,0.0002619423,0.00032191],"domain_scores_gemma":[0.999115,0.0002740714,0.00009481426,0.0002492309,0.0001486519,0.0001182166],"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":[0.00006931023,0.000004963888,1.242146e-7,0.0001113715,0.00001328959,0.000002646218,0.0007024293,0.04129449,0.4081609,1.189555e-7,0.0000180778,0.5496223],"study_design_scores_gemma":[0.0007495104,0.00003713439,0.00001316948,0.0001037225,0.0000556293,0.00001652972,0.0001385965,0.6553237,0.3433324,0.00004382126,0.00001897765,0.0001668075],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07885315,0.00003069376,0.9192908,0.0007661034,0.0003232131,0.00047505,0.00001583702,0.0001886902,0.00005645487],"genre_scores_gemma":[0.5864987,0.0000794238,0.4131646,0.0001638495,0.00002208871,3.477534e-8,0.000001953745,0.00002471591,0.00004459183],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6140292,"threshold_uncertainty_score":0.9999982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02970170866786325,"score_gpt":0.2620758276135057,"score_spread":0.2323741189456424,"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."}}