{"id":"W2963896595","doi":"10.1109/cvpr.2018.00908","title":"SBNet: Sparse Blocks Network for Fast Inference","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":202,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; FLOPS; Computation; Convolution (computer science); Speedup; Convolutional neural network; Inference; Artificial intelligence; Leverage (statistics); Object detection; Pattern recognition (psychology); Algorithm; Parallel computing; Artificial neural network","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":[0.0005861849,0.001205599,0.0007238656,0.0006528852,0.0003879248,0.0007512487,0.001802379,0.001149475,0.01047213],"category_scores_gemma":[0.002623605,0.000757599,0.0005138088,0.000756243,0.0005190409,0.00178452,0.001060281,0.001646877,0.004524161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009849848,"about_ca_system_score_gemma":0.001753118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01154865,"about_ca_topic_score_gemma":0.02352336,"domain_scores_codex":[0.9997017,0.00006312643,0.00001661238,0.00008005097,0.00009687129,0.00004170501],"domain_scores_gemma":[0.9995219,0.0001740979,0.00004497839,0.0001100109,0.0001133862,0.00003569646],"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":[0.0005645545,0.0001613692,0.001211255,0.0003182644,0.0001758119,0.0001761837,0.00008610156,0.4045001,0.02519062,0.0383359,0.04982665,0.4794532],"study_design_scores_gemma":[0.00001557479,0.00001649646,0.00005929889,0.000006191503,0.000004902503,0.00001505786,0.00000323335,0.988488,0.002945237,0.005857116,0.002584632,0.000004205115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007849567,0.0004056783,0.9766504,0.0002734077,0.0001066917,0.00007248682,0.0006779425,0.01102256,0.002941266],"genre_scores_gemma":[0.2340666,0.0005097936,0.7463709,0.0003956888,0.0001265153,0.0004936577,0.004547115,0.001600894,0.0118889],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01154865,"threshold_uncertainty_score":0.03503275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03360285784287599,"score_gpt":0.2991795134082915,"score_spread":0.2655766555654155,"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."}}