{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008302907,0.0008611645,0.0008934375,0.0007787981,0.0003627595,0.001390369,0.001744649,0.0010108,0.003674794],"category_scores_gemma":[0.006769738,0.0003164206,0.0004901965,0.0008701917,0.0008448947,0.003633446,0.002036408,0.001869257,0.0008731825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009258562,"about_ca_system_score_gemma":0.001249384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005326925,"about_ca_topic_score_gemma":0.006384024,"domain_scores_codex":[0.9991509,0.0001500988,0.00005524753,0.0001745189,0.0004142259,0.00005495012],"domain_scores_gemma":[0.9983653,0.0005177946,0.0001410268,0.0006020126,0.0003158033,0.00005802949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003883621,0.0001540558,0.001519294,0.0002365574,0.00007158142,0.0001935306,0.0001925505,0.3525913,0.03311612,0.03879208,0.01617831,0.5565663],"study_design_scores_gemma":[0.00001432553,0.00003422236,0.0001614589,0.00001115354,0.000006018973,0.00004826895,0.00001746761,0.976982,0.008284084,0.01255235,0.001876142,0.0000125414],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04948902,0.0008349071,0.9405193,0.0009020708,0.000158215,0.0000763513,0.0008340607,0.004663217,0.002522916],"genre_scores_gemma":[0.5154283,0.0005398731,0.4766545,0.0007249959,0.00008697448,0.0001485422,0.002354897,0.0007267704,0.003335122],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005326925,"threshold_uncertainty_score":0.01229346,"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."}}