{"id":"W3202932137","doi":"10.48550/arxiv.2104.02424","title":"Teacher-Student Adversarial Depth Hallucination to Improve Face Recognition","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Face recognition and analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Discriminator; Hallucinating; Computer science; RGB color model; Artificial intelligence; Face (sociological concept); Generator (circuit theory); Depth map; Pattern recognition (psychology); Computer vision; Facial recognition system; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001530235,0.0001283962,0.0001418054,0.0001638536,0.000139332,0.0001122852,0.0003867124,0.00007536172,0.0001533552],"category_scores_gemma":[0.00007193389,0.000153882,0.000123654,0.001054767,0.00001693734,0.0005596402,0.0002437163,0.00012504,0.0007429324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001504691,"about_ca_system_score_gemma":0.00007915023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004487105,"about_ca_topic_score_gemma":0.0001910371,"domain_scores_codex":[0.9987954,0.0001196399,0.0001257046,0.0006278755,0.0001084268,0.0002229199],"domain_scores_gemma":[0.9991003,0.00004423278,0.00006972684,0.0003724318,0.0002435285,0.0001698149],"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":[0.0001821158,0.002909967,0.01110936,0.0001003785,0.001017672,0.002716165,0.005933249,0.08957849,0.03041432,0.06416623,0.003532143,0.7883399],"study_design_scores_gemma":[0.004570294,0.000371213,0.0122409,0.0001038577,0.0003677044,0.00003289845,0.003792696,0.9276918,0.03131264,0.0100517,0.00782854,0.0016358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2473074,0.000009590423,0.7463441,0.0004540374,0.0002673833,0.0001019176,0.000005466839,0.0001322655,0.005377834],"genre_scores_gemma":[0.9920883,0.00003122641,0.003154554,0.0004032721,0.00006301643,8.805971e-7,0.00002269975,0.000006765376,0.004229263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8381132,"threshold_uncertainty_score":0.954914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0526758888711047,"score_gpt":0.2001021225386933,"score_spread":0.1474262336675886,"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."}}