{"id":"W2913081068","doi":"10.1109/tnnls.2019.2892035","title":"Balanced Decoupled Spatial Convolution for CNNs","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Guangzhou Municipal Science and Technology Project; National Natural Science Foundation of China","keywords":"Redundancy (engineering); Convolution (computer science); Computer science; Decoupling (probability); Filter (signal processing); Algorithm; Spatial analysis; Channel (broadcasting); Spatial filter; Artificial intelligence; Mathematics; Computer vision; Engineering; Telecommunications","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004331787,0.001079216,0.0005786987,0.0004017117,0.0003080087,0.000567409,0.001045855,0.0006670035,0.003116464],"category_scores_gemma":[0.00109208,0.000410372,0.0007218441,0.0005426733,0.0005495371,0.001904038,0.001050235,0.00113056,0.001012817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009073309,"about_ca_system_score_gemma":0.000854976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00327183,"about_ca_topic_score_gemma":0.005794794,"domain_scores_codex":[0.9997458,0.00004140146,0.00001428438,0.00006587818,0.00008254436,0.00005000418],"domain_scores_gemma":[0.999741,0.0000748677,0.00002813741,0.00007735012,0.00005856896,0.00002009439],"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":[0.000296336,0.000103393,0.0009305275,0.0001877774,0.00009726307,0.0002023899,0.00007036624,0.6463246,0.05116569,0.05036085,0.004866758,0.245394],"study_design_scores_gemma":[0.000004874672,0.00002354513,0.00008930423,0.000004479043,0.000008962918,0.00003354669,0.000005112472,0.9854376,0.005517336,0.007715941,0.001155381,0.000003902327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01952274,0.0003110587,0.9760519,0.0001404901,0.00004343874,0.00002473293,0.0001106408,0.001271761,0.002523219],"genre_scores_gemma":[0.6495847,0.0006385631,0.3399663,0.0002480203,0.00007187846,0.0001254006,0.0006630219,0.0002606944,0.00844138],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00327183,"threshold_uncertainty_score":0.01042557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01063734284848073,"score_gpt":0.233604971592646,"score_spread":0.2229676287441653,"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."}}