{"id":"W4200061105","doi":"10.1016/j.patrec.2021.12.004","title":"A discriminative channel diversification network for image classification","year":2021,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Agricultural Research Service; National Institutes of Health; U.S. Department of Agriculture","keywords":"Discriminative model; Computer science; Margin (machine learning); Computation; Convolutional neural network; Channel (broadcasting); Block (permutation group theory); Plug-in; Artificial intelligence; Context (archaeology); Pattern recognition (psychology); Machine learning; Algorithm; Computer network; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004844181,0.0004888976,0.0007980467,0.000419374,0.0003321793,0.0004239692,0.001406779,0.0009100031,0.003338411],"category_scores_gemma":[0.0007495357,0.00029853,0.0003701956,0.0005523223,0.0004423838,0.0007881667,0.001376769,0.0009170726,0.0008779613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000400229,"about_ca_system_score_gemma":0.0005504857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001876476,"about_ca_topic_score_gemma":0.003224444,"domain_scores_codex":[0.9998218,0.00003674295,0.000008035888,0.00005311456,0.00004647217,0.00003387306],"domain_scores_gemma":[0.9997526,0.00007295772,0.00001831647,0.0000473711,0.00007633997,0.00003230096],"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":[0.000399649,0.0002357216,0.001241099,0.000109477,0.0001095648,0.000129383,0.0000645506,0.189938,0.04934156,0.01933811,0.009489093,0.7296038],"study_design_scores_gemma":[0.00001323767,0.00004737217,0.0001641298,0.000004298717,0.00001248551,0.00003479868,0.000004822979,0.9920894,0.003220643,0.003495866,0.0009070838,0.000005861792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04204394,0.0006387068,0.9526535,0.0002282513,0.00008938686,0.00006362703,0.0001137017,0.0008140658,0.00335491],"genre_scores_gemma":[0.6075609,0.0004705693,0.3777139,0.0005615499,0.0001554122,0.0001634346,0.0005424271,0.0001458388,0.01268584],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003338411,"threshold_uncertainty_score":0.01116806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06345785352901455,"score_gpt":0.2815284641893757,"score_spread":0.2180706106603612,"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."}}