{"id":"W4298018940","doi":"10.48550/arxiv.1806.07987","title":"A Hierarchical Deep Architecture and Mini-Batch Selection Method For\\n Joint Traffic Sign and Light Detection","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Benchmark (surveying); Traffic sign; Software deployment; Deep learning; Memory footprint; Artificial intelligence; Traffic sign recognition; Convolutional neural network; Host (biology); Graphics processing unit; Real-time computing; Sign (mathematics)","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"],"consensus_categories":[],"category_scores_codex":[0.0002361944,0.0003108977,0.0003091315,0.0002693174,0.0003699932,0.0001077324,0.0004613579,0.0003111433,0.000002319421],"category_scores_gemma":[0.00003932342,0.0003404769,0.0001102222,0.0005706629,0.000128561,0.0001875535,0.0006880563,0.0005991556,0.000003193239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000105583,"about_ca_system_score_gemma":0.00005591976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001064483,"about_ca_topic_score_gemma":0.0001417989,"domain_scores_codex":[0.9978344,0.0001895689,0.0001932779,0.001377948,0.00007110152,0.0003336671],"domain_scores_gemma":[0.9986507,0.0002910294,0.0002040238,0.0005237506,0.0001315592,0.0001988959],"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":[0.0003093927,0.0001881753,0.0001338417,0.0003271376,0.0002307657,0.00003784106,0.001679531,0.539739,0.006673652,0.05154615,0.0002687553,0.3988658],"study_design_scores_gemma":[0.0003702437,0.0001969704,0.0003512777,0.00003052107,0.00006590544,0.0000492978,0.00001506697,0.8690652,0.001520473,0.1268928,0.001090025,0.0003521144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1070979,0.00006526948,0.89127,0.0004098492,0.0001574538,0.0006776534,0.000004278718,0.000252519,0.00006510794],"genre_scores_gemma":[0.7851427,0.00009001112,0.2143181,0.00008343835,0.00017369,0.00001418965,0.000004913692,0.00002178035,0.0001511835],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6780448,"threshold_uncertainty_score":0.9999048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.039998841520913,"score_gpt":0.2125664140089716,"score_spread":0.1725675724880585,"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."}}