{"id":"W4404954931","doi":"10.5753/sibgrapi.est.2024.31662","title":"A Comparative Study on Synthetic Facial Data Generation Techniques for Face Recognition","year":2024,"lang":"en","type":"article","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Semtech (Canada)","funders":"Fundação da Universidade Federal do Paraná; Universidade Federal do Paraná; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Computer science; Biometrics; Facial recognition system; Artificial intelligence; Robustness (evolution); Benchmarking; Machine learning; Synthetic data; Benchmark (surveying); Discriminative model; Data science; Pattern recognition (psychology)","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":[0.0003240284,0.0001027472,0.0001354146,0.000164405,0.0001070183,0.0003977269,0.0003882376,0.00003103317,0.00004951004],"category_scores_gemma":[0.00002699665,0.00008217897,0.0000475913,0.0002986893,0.0000128845,0.0005221232,0.0001026395,0.00006590387,0.0002870061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002473008,"about_ca_system_score_gemma":0.00003163823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001032095,"about_ca_topic_score_gemma":0.00005145033,"domain_scores_codex":[0.9989581,0.00007348281,0.0001625106,0.0005280711,0.0001677262,0.0001101581],"domain_scores_gemma":[0.9993607,0.00009753818,0.00002452951,0.0004134174,0.00006864783,0.00003513528],"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":[0.000009695567,0.0005237559,0.000006367975,0.00002092148,0.0001432408,0.000006538795,0.00230148,0.00002421789,0.005794335,0.002478366,0.01868265,0.9700084],"study_design_scores_gemma":[0.0001470832,0.0004126741,0.00001659572,0.00003893556,0.00005466105,0.000003039781,0.0007763831,0.9479172,0.04040977,0.001147064,0.008858317,0.0002182955],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009239868,0.00002454042,0.9863378,0.0008439251,0.0002017964,0.0006524692,0.00009181322,0.0005068515,0.002100914],"genre_scores_gemma":[0.9719737,0.000008393147,0.02683537,0.000184671,0.0001142412,0.0001414425,0.0002134503,0.000005997802,0.0005228099],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9697902,"threshold_uncertainty_score":0.383529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2147572229219608,"score_gpt":0.3828580308243992,"score_spread":0.1681008079024384,"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."}}