{"id":"W2948781670","doi":"10.1109/cvpr.2019.01196","title":"Deep Spherical Quantization for Image Search","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Codebook; Hypersphere; Quantization (signal processing); Artificial intelligence; Convolutional neural network; Discriminative model; Pattern recognition (psychology); Learning vector quantization; Computer science; Vector quantization; Deep learning; Binary number; Hash function; Binary code; Mathematics; Linde–Buzo–Gray algorithm; Algorithm","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":[0.0005235079,0.0003791275,0.0005957718,0.0006687785,0.0002238531,0.0007018854,0.0007686163,0.0004931956,0.003114381],"category_scores_gemma":[0.002573741,0.0001667911,0.0003173191,0.001258311,0.0005601427,0.001787385,0.001013538,0.0008186412,0.001047851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008566603,"about_ca_system_score_gemma":0.0007580265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003615367,"about_ca_topic_score_gemma":0.004007896,"domain_scores_codex":[0.9995114,0.0001015759,0.00003340735,0.00007872069,0.0002403417,0.00003463421],"domain_scores_gemma":[0.9995185,0.0001500151,0.0000465839,0.0001273263,0.0001336931,0.00002387223],"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":[0.0002025776,0.0000582164,0.0005670546,0.000280778,0.000037586,0.00004636288,0.00009306085,0.1808565,0.01651906,0.1547164,0.01390819,0.632714],"study_design_scores_gemma":[0.00002381035,0.00006350184,0.0002850067,0.00002118417,0.000008763927,0.0000679386,0.00002760927,0.9023652,0.008388458,0.07964778,0.009081545,0.00001925755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009377894,0.002156563,0.9840771,0.0002984279,0.00008763778,0.00004202497,0.0002717727,0.0009338825,0.002754677],"genre_scores_gemma":[0.503921,0.003355525,0.4822039,0.0003638941,0.0002034496,0.0001995183,0.001419583,0.0002129979,0.008120125],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003615367,"threshold_uncertainty_score":0.01041859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03927770747081652,"score_gpt":0.3537550708310025,"score_spread":0.3144773633601861,"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."}}