{"id":"W4404838659","doi":"10.1016/j.neucom.2024.128998","title":"Depth-Wise Convolutions in Vision Transformers for efficient training on small datasets","year":2024,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Transformer; Artificial intelligence; Training (meteorology); Pattern recognition (psychology); Training set; Machine learning; Computer vision; Electrical engineering; Geography; Engineering; Voltage","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002345568,0.0001665002,0.0001489406,0.000209123,0.0002195299,0.0001392274,0.0004483138,0.0000607339,9.428516e-7],"category_scores_gemma":[0.00003337782,0.0001661462,0.00007990484,0.0007979344,0.00003264544,0.0001468838,0.00009600254,0.0003623469,0.00002268838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006329863,"about_ca_system_score_gemma":0.00005241457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002589942,"about_ca_topic_score_gemma":0.00002083324,"domain_scores_codex":[0.99836,0.00004304718,0.0003113491,0.0006922568,0.0001489269,0.0004444451],"domain_scores_gemma":[0.998771,0.0008089055,0.00004210355,0.0002667285,0.00001815039,0.00009317251],"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":[0.000008454338,0.00008862777,0.00001179001,0.00005403216,0.000005420351,0.00003056537,0.0008020399,0.2867072,0.003612602,0.04034752,0.0006649986,0.6676667],"study_design_scores_gemma":[0.0002680843,0.00006350057,0.0007203643,0.0001340851,0.000004088849,0.00001537231,0.00001963986,0.9784673,0.0004486675,0.0006602875,0.01903646,0.0001621101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03583696,0.00009142116,0.9601361,0.00201169,0.0004175159,0.0006994104,0.00002212135,0.0004174162,0.0003674112],"genre_scores_gemma":[0.9646073,0.000007132588,0.03456594,0.000552394,0.0001092489,0.00008652458,0.00003473034,0.00002390376,0.00001283446],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9287704,"threshold_uncertainty_score":0.6775244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04759880997046345,"score_gpt":0.3174072731901771,"score_spread":0.2698084632197136,"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."}}