{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00115875,0.001829789,0.001113424,0.00129865,0.0005033461,0.001147938,0.003152193,0.001483088,0.006001854],"category_scores_gemma":[0.002321039,0.0006561777,0.001449987,0.0005689546,0.0005749004,0.001611597,0.002611631,0.002565574,0.004580075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007231106,"about_ca_system_score_gemma":0.0008776376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00352731,"about_ca_topic_score_gemma":0.005539466,"domain_scores_codex":[0.9991702,0.00008867093,0.00002504525,0.0002997017,0.0002875989,0.0001288518],"domain_scores_gemma":[0.9993542,0.0001387329,0.00003659829,0.0002669298,0.0001598392,0.0000437132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000489427,0.0003825474,0.002003214,0.0002175279,0.0002344566,0.0001983977,0.00009784536,0.04888032,0.05984459,0.005674533,0.03519347,0.8467836],"study_design_scores_gemma":[0.00002597392,0.0001537016,0.0008852776,0.0000288355,0.00003947887,0.0002963399,0.00002703956,0.9222593,0.05913162,0.006592579,0.01052536,0.00003434242],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01249235,0.000383702,0.9663576,0.0002323669,0.0001891875,0.0001594598,0.0007336724,0.01731874,0.002132917],"genre_scores_gemma":[0.1852878,0.0004472001,0.7964306,0.0008157477,0.0001394642,0.0004728968,0.004747988,0.001431212,0.01022712],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006001854,"threshold_uncertainty_score":0.02007824,"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."}}