{"id":"W4312477916","doi":"10.1109/cvpr52688.2022.01404","title":"Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Consistency (knowledge bases); Computer science; Margin (machine learning); Code (set theory); Sample (material); Point (geometry); Momentum (technical analysis); Algorithm; Artificial intelligence; Machine learning; Chemistry; Mathematics; Programming language","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":[0.002655588,0.0009786506,0.001416381,0.0006565661,0.0006088876,0.002059591,0.002232679,0.001929048,0.003608717],"category_scores_gemma":[0.015349,0.000455518,0.0006333053,0.0005372771,0.002041996,0.004234856,0.004290377,0.003645646,0.001387453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008832445,"about_ca_system_score_gemma":0.001897736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002492869,"about_ca_topic_score_gemma":0.003212335,"domain_scores_codex":[0.9987165,0.0004412531,0.00006606351,0.000274856,0.0003231033,0.0001781933],"domain_scores_gemma":[0.9958936,0.001754765,0.0002637175,0.001131329,0.0006685356,0.0002881312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001240828,0.0005789463,0.004706006,0.0005171914,0.0001287846,0.0004293602,0.0004835984,0.4170514,0.02802072,0.1779857,0.01672059,0.3521369],"study_design_scores_gemma":[0.00003781042,0.00008044076,0.0002060004,0.00003838066,0.00001246838,0.00007488763,0.00003148484,0.9573208,0.002915642,0.03597132,0.003295683,0.00001505693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02683381,0.000916617,0.9650642,0.001013566,0.0001276562,0.00009088427,0.00009728751,0.001883353,0.003972684],"genre_scores_gemma":[0.5842587,0.0009511563,0.4030984,0.001819171,0.0004023683,0.0003354256,0.0004230794,0.001302644,0.007409101],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003608717,"threshold_uncertainty_score":0.01404423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08498805987629938,"score_gpt":0.2888137516274756,"score_spread":0.2038256917511762,"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."}}