{"id":"W4226195328","doi":"10.1109/tcsvt.2022.3169145","title":"Extending Momentum Contrast With Cross Similarity Consistency Regularization","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Regularization (linguistics); Artificial intelligence; Contrast (vision); Computer science; Similarity (geometry); Machine learning; Consistency (knowledge bases); Pattern recognition (psychology); Mathematics; Theoretical computer science; Image (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":[0.002109074,0.0009111097,0.0008664452,0.0006960426,0.0004250116,0.001143504,0.001754309,0.001507344,0.001599829],"category_scores_gemma":[0.007038273,0.0003446565,0.0004926956,0.0005862573,0.001296174,0.002305327,0.002526193,0.001941478,0.0004587271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007600138,"about_ca_system_score_gemma":0.0009829608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00139235,"about_ca_topic_score_gemma":0.001735543,"domain_scores_codex":[0.9991024,0.0002876573,0.00003552851,0.0002158651,0.000285305,0.00007343139],"domain_scores_gemma":[0.9980004,0.0008108816,0.0002261229,0.0004798334,0.0003739196,0.0001087325],"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":[0.0005584595,0.0004989881,0.006712423,0.0001842322,0.0002207362,0.0002773917,0.0003075434,0.4396024,0.03069269,0.07202972,0.009078565,0.4398368],"study_design_scores_gemma":[0.00002044851,0.00007056094,0.0002934848,0.000006939954,0.000007605486,0.00004567385,0.000007341456,0.9866813,0.002474571,0.009702805,0.0006814875,0.000007724172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06111367,0.0003142807,0.9334259,0.0005241834,0.0000821265,0.00007324558,0.00007693632,0.001465342,0.002924448],"genre_scores_gemma":[0.8113302,0.0001570222,0.1823263,0.0005741947,0.0002029336,0.0001449232,0.0003037332,0.0003741698,0.00458656],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002109074,"threshold_uncertainty_score":0.011154,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02180540015078219,"score_gpt":0.2519685642694048,"score_spread":0.2301631641186226,"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."}}