{"id":"W2177568369","doi":"10.1109/cvpr.2016.619","title":"Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Canadian Institute for Advanced Research; Université de Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Compute Canada; National Aeronautics and Space Administration","keywords":"Pooling; Computer science; Artificial intelligence; Robustness (evolution); Pattern recognition (psychology); Convolutional neural network; Upsampling; Feature (linguistics); Concatenation (mathematics); Computation; Pixel; Segmentation; Image (mathematics); Algorithm; 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":[0.001479419,0.001933837,0.001146704,0.0007096122,0.0003479017,0.001119353,0.002713576,0.001260815,0.002354592],"category_scores_gemma":[0.002003391,0.0007139137,0.000931056,0.0007698305,0.000966072,0.003339995,0.002036306,0.002141023,0.001116149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009428275,"about_ca_system_score_gemma":0.0008256032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003675152,"about_ca_topic_score_gemma":0.0062725,"domain_scores_codex":[0.9995302,0.00008220694,0.00001985335,0.0001838221,0.0001175858,0.0000663148],"domain_scores_gemma":[0.999506,0.0001390629,0.00007998822,0.0001654526,0.0000755917,0.00003404359],"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":[0.0004420771,0.0002947222,0.00159651,0.0001398866,0.0002200191,0.0002083339,0.0001598606,0.4749167,0.03271513,0.01762675,0.00881453,0.4628655],"study_design_scores_gemma":[0.00001259458,0.00007101386,0.0001814264,0.000006894155,0.00001944821,0.00002856445,0.000007802482,0.9858322,0.006233016,0.006334124,0.001263552,0.000009494764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02401963,0.00057294,0.9677433,0.0001879174,0.00006700472,0.00006302252,0.0001561902,0.005381901,0.001808028],"genre_scores_gemma":[0.5359761,0.0007164765,0.4484587,0.0005615746,0.0001570996,0.0002622283,0.001137822,0.0006709006,0.01205904],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003675152,"threshold_uncertainty_score":0.007876873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01308071279119167,"score_gpt":0.2437948723887083,"score_spread":0.2307141595975167,"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."}}