{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003630528,0.0002710333,0.000345403,0.0002892888,0.0001346574,0.0003982,0.0008735863,0.0003211006,0.0002611514],"category_scores_gemma":[0.0001173933,0.0002079182,0.0002305728,0.0004328243,0.00001775469,0.0001931372,0.001125986,0.0006565991,0.0005961267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009277416,"about_ca_system_score_gemma":0.00007420332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001330718,"about_ca_topic_score_gemma":0.00002383536,"domain_scores_codex":[0.9982255,0.0001602341,0.0002463589,0.0007531167,0.0002960399,0.0003187607],"domain_scores_gemma":[0.9986301,0.00009429779,0.0002055,0.0006259208,0.0002369334,0.0002072706],"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":[0.00000716238,0.00006667275,0.0003918872,0.0000473075,0.0001598162,0.00001753367,0.0001696944,0.01425116,0.00008932406,0.01217463,0.04351942,0.9291054],"study_design_scores_gemma":[0.0005190906,0.00008401921,0.0002315618,0.0008636755,0.00005606222,0.0000101913,0.00002688581,0.9302882,0.0009716767,0.02140446,0.0445617,0.0009824891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000823884,0.0001740553,0.974461,0.013853,0.001127575,0.0002167322,0.000002740171,0.0005775164,0.008763482],"genre_scores_gemma":[0.6495874,0.0007530702,0.1790125,0.004128697,0.001143045,0.0002260037,0.0002299434,0.0001072175,0.1648121],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9281229,"threshold_uncertainty_score":0.847866,"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."}}