{"id":"W4224224489","doi":"10.3390/jimaging8050118","title":"Discriminative Shape Feature Pooling in Deep Neural Networks","year":2022,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Discriminative model; Artificial intelligence; Leverage (statistics); Deep learning; Pooling; Deep neural networks; Benchmark (surveying); Machine learning; Domain knowledge; Artificial neural network; Domain (mathematical analysis); Feature (linguistics); Pattern recognition (psychology); Process (computing)","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":[0.0005838734,0.001265225,0.0009591303,0.0007131348,0.0003028946,0.000597889,0.001620618,0.0007097499,0.001519442],"category_scores_gemma":[0.001106601,0.0005681771,0.0008249977,0.001110781,0.0006885913,0.001868254,0.000961336,0.001042342,0.0005455878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001113434,"about_ca_system_score_gemma":0.0006811594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006280235,"about_ca_topic_score_gemma":0.009710269,"domain_scores_codex":[0.999692,0.00003478023,0.00001713471,0.000122059,0.00008038573,0.00005365712],"domain_scores_gemma":[0.9997813,0.00004936887,0.00003881568,0.00006585627,0.00004803182,0.00001654057],"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":[0.0001671016,0.00009396123,0.0008277152,0.000115194,0.00008881473,0.0001241695,0.00005311154,0.5092726,0.02778016,0.01074631,0.003478508,0.4472524],"study_design_scores_gemma":[0.000007129986,0.00002746736,0.0002391136,0.000005401443,0.00001265705,0.00003029096,0.000006073109,0.9853145,0.007844396,0.00561919,0.000885867,0.000007963722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03091635,0.0006222597,0.9639688,0.0001467321,0.00005805062,0.00005108674,0.0002167242,0.002125826,0.001894063],"genre_scores_gemma":[0.7090307,0.000640125,0.2823518,0.0002833041,0.0000814197,0.0001389343,0.001125982,0.0002439351,0.006103725],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006280235,"threshold_uncertainty_score":0.01248735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01005168950501387,"score_gpt":0.2755248942184061,"score_spread":0.2654732047133923,"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."}}