{"id":"W4404914900","doi":"10.1109/tgrs.2024.3509735","title":"SECBNet: Semantic Segmentation-Enhanced Color Balance Network for Optical Satellite Images","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for Central Universities of the Central South University; Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"Computer science; Segmentation; Artificial intelligence; Satellite; Image segmentation; Remote sensing; Balance (ability); Computer vision; Pattern recognition (psychology); Geology; Astronomy","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":[0.0002206052,0.0001910839,0.0001681992,0.0001271244,0.0003015571,0.0002631759,0.00006092607,0.00008903901,0.000002420732],"category_scores_gemma":[0.000008901982,0.0001828273,0.00007088752,0.0004626614,0.0001791773,0.0002704676,9.168776e-7,0.0002029097,0.00002499385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000850184,"about_ca_system_score_gemma":0.00003303293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001390744,"about_ca_topic_score_gemma":0.00002496047,"domain_scores_codex":[0.9987874,0.00001844561,0.0002414022,0.0003978036,0.0001778567,0.0003770844],"domain_scores_gemma":[0.9993973,0.0002438241,0.00002135338,0.0001874599,0.00005820408,0.0000918155],"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":[0.000009813127,0.000004532033,9.829044e-8,0.00009611159,0.00001689246,0.000007064772,0.000199872,0.03067385,0.2669185,0.000007096728,0.00006713263,0.701999],"study_design_scores_gemma":[0.0001187278,0.00004013157,0.000091076,0.0002576193,0.00003166941,0.00005060527,0.00007840819,0.8339275,0.1644689,0.0001740809,0.0005735056,0.0001878942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04672206,0.0003552339,0.9497342,0.0002996468,0.001781376,0.0003253841,0.0000101518,0.0004312401,0.0003406912],"genre_scores_gemma":[0.7544169,0.0008115809,0.2440695,0.00007302799,0.0001388329,5.542182e-7,0.000004067152,0.00003977485,0.0004456968],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8032536,"threshold_uncertainty_score":0.7455482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01259964287849635,"score_gpt":0.2477645873065802,"score_spread":0.2351649444280838,"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."}}