{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007025251,0.0004295846,0.000482179,0.0003773523,0.00146736,0.001086807,0.0003312349,0.0001165348,0.0005033424],"category_scores_gemma":[0.00004547657,0.0004234085,0.00009370645,0.0004090649,0.0001296023,0.0006340934,0.0004964313,0.001193281,0.00003318183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001541277,"about_ca_system_score_gemma":0.0001041654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004079688,"about_ca_topic_score_gemma":0.00001276526,"domain_scores_codex":[0.9965113,0.0007997588,0.0004587116,0.001041161,0.0007063574,0.0004826527],"domain_scores_gemma":[0.998508,0.0004664344,0.0003205946,0.0002456295,0.0001765747,0.0002827633],"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":[0.0003014003,0.0002495194,0.002249237,0.0001231721,0.0001782499,0.0002171641,0.0171325,0.001431593,0.00469628,0.006967768,0.001289779,0.9651634],"study_design_scores_gemma":[0.005372804,0.003137539,0.01194053,0.0006451602,0.00005420604,0.0004343626,0.01272874,0.9500809,0.0007299056,0.01048758,0.00271878,0.001669488],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1739138,0.00005211197,0.8216231,0.001569651,0.0008857365,0.0005214128,0.00006577659,0.0002885778,0.001079805],"genre_scores_gemma":[0.9920655,0.0001294065,0.004247333,0.002979364,0.0001771929,0.00007088469,0.00009222153,0.00003357224,0.000204474],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9634938,"threshold_uncertainty_score":0.9999502,"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."}}