{"id":"W3121483733","doi":"10.15353/jcvis.v6i1.3534","title":"Acceleration of Large Margin Metric Learning for Nearest Neighbor Classification Using Triplet Mining and Stratified Sampling","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Metric (unit); Margin (machine learning); Large margin nearest neighbor; Subspace topology; k-nearest neighbors algorithm; Computer science; Artificial intelligence; Nearest neighbor search; Acceleration; Pattern recognition (psychology); Sampling (signal processing); Machine learning; Projection (relational algebra); Scalability; Nearest neighbor graph; Nonlinear dimensionality reduction; Data mining; Algorithm; Physics; Dimensionality reduction; Filter (signal processing); Computer vision; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000196788,0.00007850795,0.0001200309,0.0001657446,0.0002190146,0.00008710205,0.0001310989,0.00006625242,0.00001289567],"category_scores_gemma":[0.0001208138,0.00009201323,0.00004391843,0.0007219451,0.00001644115,0.0005935819,0.00007997866,0.00006667231,0.00000120955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003012604,"about_ca_system_score_gemma":0.00007037756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000937003,"about_ca_topic_score_gemma":0.00001458736,"domain_scores_codex":[0.9992515,0.00007507604,0.0001364413,0.0003374171,0.00005057916,0.0001489235],"domain_scores_gemma":[0.9992784,0.0001874526,0.0001423125,0.0001594431,0.000183038,0.00004931194],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002578258,0.0004880075,0.04414336,0.0004208859,0.0001614958,0.00006626791,0.002332418,0.1455654,0.5098888,0.249189,0.0002729377,0.04721354],"study_design_scores_gemma":[0.0007066652,0.0000399587,0.005492256,0.00004297273,0.00002329779,0.000002338048,0.0008205568,0.9816946,0.01009591,0.0007188863,0.000245474,0.0001171263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4796801,0.00002390215,0.5200462,0.00002913465,0.00004576676,0.00006475949,0.000002479662,0.00002076774,0.0000868885],"genre_scores_gemma":[0.9801868,0.00003512536,0.01955415,0.00002731507,0.00001973496,5.442028e-7,0.0000252726,0.000005335666,0.0001457163],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8361291,"threshold_uncertainty_score":0.3752191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1931984932620432,"score_gpt":0.2493415106867903,"score_spread":0.05614301742474709,"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."}}