{"id":"W4299509637","doi":"10.48550/arxiv.1802.06488","title":"Tiny SSD: A Tiny Single-shot Detection Deep Convolutional Neural Network\\n for Real-time Embedded Object Detection","year":2018,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Object detection; Convolutional neural network; Computer science; Artificial intelligence; Deep learning; Object (grammar); Stack (abstract data type); Artificial neural network; Feature (linguistics); Computer vision; Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001697717,0.0003818668,0.0001723262,0.0002233322,0.0001345531,0.0003071053,0.001300259,0.0002566573,0.003533542],"category_scores_gemma":[0.0004626373,0.0002042471,0.0001878578,0.0001861063,0.0001852524,0.0009159707,0.0007232329,0.000441583,0.0006212584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005739409,"about_ca_system_score_gemma":0.0006853143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005084174,"about_ca_topic_score_gemma":0.01405733,"domain_scores_codex":[0.9998947,0.000005241447,0.000003813269,0.00002383553,0.00005579381,0.00001660147],"domain_scores_gemma":[0.9999065,0.00001889413,0.000009101824,0.0000207289,0.00002689208,0.00001784716],"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":[0.001139697,0.0003034658,0.005251176,0.0004665733,0.0002099226,0.0004551753,0.0001526315,0.04501773,0.3110389,0.01157957,0.06907693,0.5553083],"study_design_scores_gemma":[0.0001438947,0.0009585014,0.004096517,0.000036695,0.00008359994,0.0005240319,0.00006828527,0.6840156,0.2417349,0.003654727,0.06461049,0.00007280009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4137623,0.00272285,0.4914385,0.0007054655,0.0008323592,0.0003924867,0.003737732,0.05392713,0.03248124],"genre_scores_gemma":[0.72859,0.0008247982,0.2269766,0.0005656426,0.00003623772,0.0001941521,0.005821153,0.0008030054,0.03618844],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005084174,"threshold_uncertainty_score":0.01182085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07309862874550152,"score_gpt":0.2157454644595246,"score_spread":0.1426468357140231,"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."}}