{"id":"W4385583101","doi":"10.1016/j.cviu.2023.103801","title":"Deep Bregman divergence for self-supervised representations learning","year":2023,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Google (Canada)","funders":"","keywords":"Bregman divergence; Divergence (linguistics); Embedding; Artificial intelligence; Artificial neural network; Metric (unit); Representation (politics); Euclidean distance; Computer science; Supervised learning; Euclidean geometry; Pattern recognition (psychology); Deep learning; Feature learning; Mathematics; Machine learning; Applied 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":[0.002719721,0.0007994841,0.0019255,0.0009880489,0.0006350136,0.001137109,0.002974823,0.002641152,0.002231668],"category_scores_gemma":[0.008008814,0.0005964945,0.000757542,0.001126135,0.001333285,0.002921367,0.002657884,0.003873731,0.0009908873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001410019,"about_ca_system_score_gemma":0.001561661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005110999,"about_ca_topic_score_gemma":0.005743645,"domain_scores_codex":[0.9989063,0.000396189,0.00005718406,0.0002646339,0.0002743388,0.0001014197],"domain_scores_gemma":[0.9975406,0.001222276,0.0001610706,0.0004366753,0.0005071516,0.0001322595],"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":[0.0002666854,0.0003252536,0.0008496995,0.0002523084,0.0001452707,0.000106623,0.000217402,0.4804648,0.008950576,0.07741678,0.01295051,0.418054],"study_design_scores_gemma":[0.000004482937,0.00002008166,0.00008278211,0.000007792624,0.000003290834,0.00001468511,0.000006639855,0.9764245,0.0006503138,0.02238512,0.0003936471,0.000006610834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009090284,0.0006432068,0.9886618,0.0002493896,0.00004382651,0.00002959288,0.00007074815,0.0006098392,0.0006014344],"genre_scores_gemma":[0.4989569,0.0009608206,0.4841013,0.0006475385,0.0001803212,0.0003121792,0.001498863,0.0006630765,0.01267908],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005110999,"threshold_uncertainty_score":0.01438338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05154279473172417,"score_gpt":0.3063525445432608,"score_spread":0.2548097498115366,"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."}}