{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004639243,0.0001611585,0.0001670589,0.0003017016,0.0009366136,0.0007122646,0.0003491554,0.00004999957,0.0000198362],"category_scores_gemma":[0.00006160312,0.0001574929,0.00008641284,0.0006874864,0.00005387666,0.0008777851,0.0004012965,0.0001561168,0.00005849593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000725174,"about_ca_system_score_gemma":0.00002294838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000284532,"about_ca_topic_score_gemma":0.000001413283,"domain_scores_codex":[0.9985214,0.0001067381,0.0002448327,0.0005279723,0.0002482348,0.0003507496],"domain_scores_gemma":[0.9989936,0.0004337519,0.00008867411,0.0002528288,0.00007598202,0.0001551289],"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":[0.00009058751,0.0001933823,0.004087517,0.0004171144,0.0002320912,0.0001903569,0.04980306,0.01755594,0.01146696,0.5736929,0.02653036,0.3157398],"study_design_scores_gemma":[0.0007438954,0.0001369112,0.001408963,0.00003587178,0.000007218274,0.00001258438,0.001215792,0.9873226,0.00003941543,0.005487054,0.003383764,0.0002059865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002064069,0.00004440461,0.9942876,0.001088619,0.0004460361,0.0002460755,6.980056e-7,0.0008791261,0.0009433731],"genre_scores_gemma":[0.5137507,0.0001666198,0.4849685,0.0004129897,0.000138454,0.00002019651,0.00002212471,0.00002758607,0.0004928926],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9697666,"threshold_uncertainty_score":0.7203769,"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."}}