{"id":"W4313313908","doi":"10.36227/techrxiv.21656993.v1","title":"AnyFace: A Data-Centric Approach For Input-Agnostic Face Detection","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Face (sociological concept); Artificial intelligence; Face detection; Code (set theory); Annotation; Training set; Facial recognition system; Set (abstract data type); Machine learning; Deep learning; Scale (ratio); 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005788973,0.0002671672,0.000352735,0.0003819209,0.000257201,0.0004063711,0.002692857,0.0001601959,0.0002334245],"category_scores_gemma":[0.0002141379,0.0002575962,0.0002113734,0.0007417274,0.00002074999,0.0002938171,0.00515626,0.0005081482,0.00004018431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001299863,"about_ca_system_score_gemma":0.000162878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008406987,"about_ca_topic_score_gemma":0.00001582942,"domain_scores_codex":[0.9974248,0.0001370264,0.0003443585,0.001339381,0.0004265699,0.0003278596],"domain_scores_gemma":[0.997502,0.000180014,0.0002094995,0.001884301,0.0001054304,0.0001187446],"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":[0.00003440769,0.001371104,0.0001550246,0.001251434,0.0009463754,0.00001854886,0.000888705,0.1840591,0.000370593,0.002885822,0.02443315,0.7835858],"study_design_scores_gemma":[0.0002572451,0.00003268546,0.00003269825,0.000007994849,0.00009192376,0.00000680411,0.0001062281,0.9852957,0.0003060667,0.0007537677,0.01276234,0.0003465372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003056679,0.0002497099,0.9947851,0.0004510838,0.0005732034,0.0008039353,0.0002085607,0.000416358,0.002206377],"genre_scores_gemma":[0.5238498,0.0004418343,0.4640055,0.00098673,0.0002522281,0.001062044,0.00375401,0.00005429851,0.005593549],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8012366,"threshold_uncertainty_score":0.9999876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06343504470080005,"score_gpt":0.2934442384438073,"score_spread":0.2300091937430073,"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."}}