{"id":"W2895255442","doi":"10.1109/wacv.2019.00040","title":"Multi-Scale Convolution Aggregation and Stochastic Feature Reuse for DenseNets","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Overfitting; Computer science; Reuse; Convolution (computer science); Feature (linguistics); Regularization (linguistics); Concatenation (mathematics); Artificial intelligence; Scale (ratio); Aggregate (composite); Convolutional neural network; Artificial neural network; Machine learning; Algorithm; Pattern recognition (psychology); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001156584,0.00133332,0.001160305,0.0007605492,0.0004567672,0.0006504628,0.001684482,0.0007532918,0.001397336],"category_scores_gemma":[0.002348534,0.0006164919,0.0009696692,0.0009597479,0.0008646272,0.001961765,0.001878678,0.001221585,0.0005120385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008742536,"about_ca_system_score_gemma":0.0008243239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003001412,"about_ca_topic_score_gemma":0.005660947,"domain_scores_codex":[0.9993815,0.0001323261,0.00003993815,0.0002024453,0.0001578657,0.00008587774],"domain_scores_gemma":[0.9990615,0.0002307287,0.0001279212,0.0003994218,0.0001199298,0.00006046705],"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":[0.0002992415,0.0002537027,0.002322088,0.0001695528,0.000241163,0.0003013457,0.0002008283,0.5325766,0.04186545,0.03154747,0.005631159,0.3845914],"study_design_scores_gemma":[0.00000792331,0.00004949038,0.0002858102,0.000004874194,0.00001748688,0.00007063147,0.00000686924,0.9835095,0.007870258,0.007009204,0.001159211,0.000008760197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02777835,0.0002948488,0.9685251,0.00009008913,0.00003303673,0.00003346261,0.00006047998,0.002129689,0.001054905],"genre_scores_gemma":[0.6367745,0.0002981287,0.3572504,0.0002100354,0.00009595769,0.0001518328,0.0004817285,0.0004167429,0.00432063],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003001412,"threshold_uncertainty_score":0.006343186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02868478204061275,"score_gpt":0.2889173167260632,"score_spread":0.2602325346854504,"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."}}