{"id":"W4392979708","doi":"10.1109/jiot.2024.3373454","title":"Bias-Compensation Augmentation Learning for Semantic Segmentation in UAV Networks","year":2024,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"UAV Applications and Optimization","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Computer science; Segmentation; Compensation (psychology); Artificial intelligence; Computer vision; Machine learning","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":[0.0003735571,0.00008375337,0.0001011526,0.0002300235,0.0000285488,0.0001399544,0.00007370241,0.00005497438,0.00003309197],"category_scores_gemma":[0.00001488403,0.00008496601,0.0000558266,0.0001704589,0.00000968183,0.0004655482,0.000004853168,0.0002269658,0.000005061613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001328016,"about_ca_system_score_gemma":0.00001032609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001928363,"about_ca_topic_score_gemma":0.000008645549,"domain_scores_codex":[0.9992995,0.00002045115,0.0003704349,0.0000892988,0.0001071262,0.0001132213],"domain_scores_gemma":[0.9997191,0.00008022343,0.00008109747,0.00003996936,0.00005539087,0.00002423137],"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":[0.00001198393,0.00001001805,0.0005723571,0.00009141253,0.00003377635,0.000001546069,0.001903,0.9662847,0.009375771,0.0001596113,0.0007339047,0.02082193],"study_design_scores_gemma":[0.0002466813,0.00004217944,0.0003417183,0.0002478496,0.00002156952,0.00002609144,0.0001565166,0.9877049,0.01050034,0.0003657417,0.0002674887,0.00007892105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2830663,0.0002196306,0.7157223,0.00004576149,0.000613384,0.0001353236,3.894896e-7,0.00006119414,0.0001357089],"genre_scores_gemma":[0.9920429,0.0001679114,0.007409445,0.00001786058,0.0001531648,0.00002259556,0.00002405357,0.00002553663,0.0001365105],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7089766,"threshold_uncertainty_score":0.3464814,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01635055946229193,"score_gpt":0.2571201907191247,"score_spread":0.2407696312568328,"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."}}