{"id":"W2890980329","doi":"10.1109/lgrs.2018.2866816","title":"Vehicle Detection in High-Resolution Images Using Superpixel Segmentation and CNN Iteration Strategy","year":2018,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Overfitting; Artificial intelligence; Computer science; Pattern recognition (psychology); Convolutional neural network; Segmentation; Image segmentation; Object detection; Feature extraction; Feature selection; Computer vision; Artificial neural network","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004250106,0.0006131682,0.0004887522,0.0008415871,0.0002324055,0.0005054525,0.0007767318,0.0004920168,0.0006361785],"category_scores_gemma":[0.0008808572,0.0004073024,0.0005156801,0.0007632992,0.0004308135,0.001049385,0.0004131343,0.0003315797,0.000193821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007101291,"about_ca_system_score_gemma":0.000449315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005253917,"about_ca_topic_score_gemma":0.007270067,"domain_scores_codex":[0.9996866,0.00004560611,0.00001310812,0.0001019044,0.0001084663,0.00004438468],"domain_scores_gemma":[0.9997131,0.00009496493,0.00004995022,0.00004628932,0.00007688874,0.00001879207],"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":[0.0003336461,0.0001212314,0.006079068,0.0002676811,0.0001804905,0.0004500085,0.0003030018,0.2875071,0.2398306,0.006963889,0.001099732,0.4568636],"study_design_scores_gemma":[0.000003024563,0.00003174502,0.001437895,0.000004415704,0.00001734941,0.0001030269,0.00001602228,0.9766359,0.02050753,0.000781793,0.0004530265,0.00000823552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09593941,0.0004449636,0.9009334,0.00007525325,0.00001976586,0.00003915045,0.00004459237,0.0005749403,0.001928499],"genre_scores_gemma":[0.5186005,0.0003619021,0.479056,0.00006113311,0.0000214535,0.00003798434,0.0001404629,0.00008353252,0.001636956],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005253917,"threshold_uncertainty_score":0.01044667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01812167480521546,"score_gpt":0.2589676283604987,"score_spread":0.2408459535552832,"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."}}