{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.000452598,0.0001609985,0.0002544029,0.0004457828,0.001390857,0.0001961046,0.0003345927,0.00009272692,0.00001224422],"category_scores_gemma":[0.00001297942,0.0001577479,0.00005298554,0.0006324237,0.0001402108,0.0002608534,0.000006635931,0.0003177107,0.000002077194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001120171,"about_ca_system_score_gemma":0.00007851073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000176975,"about_ca_topic_score_gemma":0.000008496886,"domain_scores_codex":[0.9985108,0.00009074311,0.0003220655,0.0005008072,0.0002623171,0.0003132957],"domain_scores_gemma":[0.9991201,0.0001339112,0.0001722501,0.0003775626,0.0001266271,0.00006955635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001190442,0.0005547305,0.0008899922,0.0002797716,0.0003323491,0.00007636533,0.001671128,0.1127911,0.01198337,0.7304935,0.0002054862,0.1406031],"study_design_scores_gemma":[0.01043158,0.004728909,0.0008474747,0.0002469589,0.000170162,0.002523698,0.006522193,0.8559424,0.009486792,0.01455004,0.09263057,0.001919275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01122186,0.0002664379,0.9856921,0.0006097468,0.0007687233,0.0006771537,0.00003949553,0.0004327543,0.0002916789],"genre_scores_gemma":[0.9978221,0.00001547983,0.0006997645,0.000127779,0.00001258232,0.0005391426,0.000003314648,0.00001866174,0.0007611417],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9866003,"threshold_uncertainty_score":0.9999092,"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."}}