{"id":"W4319299845","doi":"10.1109/wacv56688.2023.00523","title":"Hyperspherical Quantization: Toward Smaller and More Accurate Models","year":2023,"lang":"en","type":"article","venue":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Quantization (signal processing); Vector quantization; Computer science; Algorithm; Linde–Buzo–Gray algorithm; Computation; Estimator; Ternary operation; Learning vector quantization; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002014818,0.0003605735,0.0004267814,0.0002872531,0.0002334847,0.0002324112,0.001587614,0.0001429724,0.00003723231],"category_scores_gemma":[0.000009009584,0.0003428331,0.0001264918,0.001798945,0.0002347224,0.0006534028,0.0006808832,0.0002933764,0.0003986574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003909132,"about_ca_system_score_gemma":0.00008105893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007903159,"about_ca_topic_score_gemma":0.000002878294,"domain_scores_codex":[0.9972556,0.00008434367,0.0006584158,0.001073272,0.0004933384,0.0004350237],"domain_scores_gemma":[0.9973527,0.0002885007,0.0002942949,0.001389406,0.0004365589,0.0002385922],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006330451,0.0004315495,0.00006384387,0.00009590009,0.00009135968,0.00001350082,0.001433245,0.06426204,0.003944318,0.5484059,0.02964791,0.3515472],"study_design_scores_gemma":[0.0004356635,0.0001952053,0.0009149899,0.00008614916,0.00001164402,0.00001515655,0.00007453486,0.9653934,0.0006351781,0.02462934,0.007223859,0.0003848559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004821436,0.00004531805,0.9825393,0.009854884,0.0002171973,0.0008547084,0.00002404371,0.0005679173,0.00107521],"genre_scores_gemma":[0.8941026,0.0003735821,0.1029321,0.0009771342,0.0002234398,0.0005514705,0.00005734671,0.0000453472,0.0007369519],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9011314,"threshold_uncertainty_score":0.9999024,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06798127665387065,"score_gpt":0.3291162494336267,"score_spread":0.261134972779756,"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."}}