{"id":"W3177177219","doi":"10.1109/tai.2021.3081057","title":"Robust Vehicle Detection in High-Resolution Aerial Images With Imbalanced Data","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Context (archaeology); Class (philosophy); Computer vision; Detector; Intersection (aeronautics); Feature (linguistics); Aerial image; Flexibility (engineering); Image (mathematics); Mathematics; 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":[0.000152538,0.0001821133,0.000174827,0.000131067,0.0003431243,0.0001898083,0.0007763444,0.00007954798,0.00003220716],"category_scores_gemma":[0.00001441108,0.0001856215,0.00003588948,0.001507764,0.0001271726,0.0008837142,0.00001590014,0.0003598597,0.00009296813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001092672,"about_ca_system_score_gemma":0.0001119507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000132006,"about_ca_topic_score_gemma":0.003093224,"domain_scores_codex":[0.9980684,0.0001044097,0.0003715136,0.0008301219,0.0002782576,0.0003472938],"domain_scores_gemma":[0.9982607,0.0001621888,0.0000901366,0.001270059,0.0001293285,0.00008758976],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008754445,0.0002695663,0.000002104052,0.000004527814,0.000009058977,0.00002581332,0.00007752448,0.6574284,0.05641139,0.003017087,0.00001045193,0.2826565],"study_design_scores_gemma":[0.00006186085,0.00007399377,0.00006129458,0.00002076105,0.000007150091,0.00001801374,0.00004375806,0.4171116,0.5793094,0.003056283,0.00006615241,0.0001696731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0186756,0.00002568964,0.9792618,0.0008702302,0.0006380071,0.0002426054,0.00002911118,0.0002128276,0.00004410948],"genre_scores_gemma":[0.9377446,0.00005548177,0.06184884,0.0001114126,0.00009518631,0.00007396314,0.000009399547,0.00001624181,0.00004485432],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.919069,"threshold_uncertainty_score":0.7569423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06558423746214823,"score_gpt":0.287204860414133,"score_spread":0.2216206229519847,"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."}}