{"id":"W2796502408","doi":"10.48550/arxiv.1804.06882","title":"Pelee: A Real-Time Object Detection System on Mobile Devices","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Pascal (unit); Object detection; Convolutional neural network; Convolution (computer science); Mobile device; Deep learning; Detector; Architecture; Artificial intelligence; Real-time computing; Computational science; Parallel computing; Pattern recognition (psychology); Artificial neural network; Operating system; Telecommunications","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001619385,0.000347767,0.000321844,0.0002460729,0.0003198596,0.0001091949,0.001799335,0.0002663062,0.0000137929],"category_scores_gemma":[0.000009449225,0.0003940032,0.0001772965,0.0008496334,0.00009786747,0.0003238177,0.001273121,0.000426174,0.00103512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005075283,"about_ca_system_score_gemma":0.00009122422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006701836,"about_ca_topic_score_gemma":0.00004044442,"domain_scores_codex":[0.9977055,0.0001543612,0.0002151979,0.001431266,0.0001219582,0.0003717557],"domain_scores_gemma":[0.9972841,0.0001706964,0.0003825981,0.001829825,0.0001720523,0.0001607616],"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":[0.0001414243,0.0002747944,0.0004747732,0.0003740612,0.0002140243,0.0003259426,0.0003667175,0.9028448,0.002594821,0.08384242,0.0008993362,0.007646887],"study_design_scores_gemma":[0.0003399444,0.0002906633,0.0007424786,0.0002574121,0.00007683391,0.00001939911,0.00006439989,0.9865191,0.003243058,0.006406025,0.001305007,0.0007356911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3900086,0.00002143583,0.5993584,0.00002038024,0.0005109744,0.0008220887,0.0000124853,0.001253472,0.007992183],"genre_scores_gemma":[0.9958283,0.00007863211,0.002657421,0.00003512771,0.000228125,0.00001466965,0.00001010006,0.00002728747,0.001120389],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6058196,"threshold_uncertainty_score":0.9998512,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03727050959129342,"score_gpt":0.1982862076473741,"score_spread":0.1610156980560806,"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."}}