{"id":"W2921599942","doi":"10.1109/wacv.2019.00133","title":"Learning Receptive Field Size by Learning Filter Size","year":2019,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Samsung","keywords":"Computer science; Filter (signal processing); Benchmark (surveying); Artificial intelligence; Convolutional neural network; Kernel (algebra); Receptive field; Backpropagation; Pattern recognition (psychology); Path (computing); Field (mathematics); Artificial neural network; Computer vision; 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":[0.0005400003,0.0006653639,0.0005719175,0.0004660428,0.0001958023,0.0005201041,0.001024651,0.0007557314,0.001101619],"category_scores_gemma":[0.002096563,0.0003394874,0.0004620595,0.0003668376,0.000561437,0.001761743,0.000588546,0.0008411189,0.0004652427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006538529,"about_ca_system_score_gemma":0.0007469815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002108183,"about_ca_topic_score_gemma":0.002754388,"domain_scores_codex":[0.9997917,0.00002811481,0.00001153766,0.0001023493,0.00004003312,0.00002620963],"domain_scores_gemma":[0.9994893,0.0002127963,0.00006985508,0.0001095558,0.00008892743,0.0000295644],"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":[0.0002208932,0.0002336441,0.004372332,0.000159877,0.000105085,0.00009596477,0.0001103533,0.3166,0.1542864,0.01046827,0.003580974,0.5097662],"study_design_scores_gemma":[0.00001797815,0.00007257089,0.0009827043,0.0000095148,0.00001969387,0.00007433856,0.00001399769,0.9676042,0.02263238,0.007503194,0.001053168,0.00001636331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07624447,0.0002578909,0.9205439,0.0001441052,0.00003718602,0.00004424068,0.0000766806,0.001146222,0.00150521],"genre_scores_gemma":[0.7103795,0.0003148296,0.2858215,0.0002255451,0.00004969014,0.0001605081,0.0002916284,0.0002311852,0.002525509],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002108183,"threshold_uncertainty_score":0.004743993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007249357642049703,"score_gpt":0.2239739305643069,"score_spread":0.2167245729222572,"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."}}