{"id":"W4372342378","doi":"10.1109/icassp49357.2023.10095678","title":"Cov Loss: Covariance-Based Loss for Deep Face Recognition","year":2023,"lang":"en","type":"article","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Artificial intelligence; Computer science; Discriminative model; Pattern recognition (psychology); Convolutional neural network; Deep learning; Facial recognition system; Face (sociological concept); Covariance matrix; Covariance; Feature (linguistics); Euclidean distance; Algorithm; Mathematics; Statistics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003002007,0.0001146465,0.00015027,0.0001941176,0.0001433229,0.0001628078,0.0003415115,0.00006300725,0.0001663635],"category_scores_gemma":[0.00008789204,0.0001054794,0.0001527342,0.001057617,0.00003255271,0.0002859468,0.00004881197,0.00005736102,0.002338433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002825031,"about_ca_system_score_gemma":0.00005627931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001390028,"about_ca_topic_score_gemma":0.00003906986,"domain_scores_codex":[0.9989248,0.00004103086,0.0001920097,0.000362643,0.0001939727,0.0002855571],"domain_scores_gemma":[0.9992007,0.0002170152,0.00006008899,0.0002699421,0.0001729647,0.00007929781],"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":[0.00006781361,0.0003590072,0.0005354133,0.000237288,0.0002265091,0.0000953839,0.0005696499,0.006485426,0.003555452,0.0178439,0.03767839,0.9323457],"study_design_scores_gemma":[0.001007172,0.00006589275,0.0001199679,0.00002797171,0.00002221858,0.000004071805,0.00008399987,0.9524402,0.02051158,0.01175929,0.01367084,0.0002867666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003305882,0.00001221667,0.9892531,0.005028124,0.0001991541,0.0002013129,0.00002454232,0.0006326549,0.001343009],"genre_scores_gemma":[0.7203358,0.00009020969,0.2646325,0.008990088,0.0001916857,0.0003490116,0.0004611328,0.0000387967,0.004910774],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9459548,"threshold_uncertainty_score":0.9984384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04575466642194836,"score_gpt":0.2772682299667377,"score_spread":0.2315135635447894,"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."}}