{"id":"W4387934025","doi":"10.2139/ssrn.4612990","title":"Open-Vocabulary Object Detection Via Debiased Curriculum Self-Training","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Vocabulary; Curriculum; Training (meteorology); Artificial intelligence; Object (grammar); Natural language processing; Psychology; Machine learning; Pedagogy; Linguistics","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":[0.0007147054,0.0005216497,0.0006226117,0.0007985248,0.0004034212,0.0006652707,0.001153748,0.0008940524,0.00537319],"category_scores_gemma":[0.002718219,0.0002218775,0.0003455392,0.0005437598,0.0003073045,0.001271395,0.002058372,0.0008220514,0.002771493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003295251,"about_ca_system_score_gemma":0.0008177945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002691663,"about_ca_topic_score_gemma":0.003877311,"domain_scores_codex":[0.9993919,0.00007943324,0.00002637863,0.0002478935,0.00012356,0.0001308542],"domain_scores_gemma":[0.9989432,0.0003105675,0.00007613035,0.0002506882,0.0003243952,0.00009511621],"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":[0.0003391241,0.0002859634,0.003850891,0.00006891639,0.00002658728,0.00006759051,0.0001300013,0.004807393,0.0551456,0.001014765,0.00301856,0.9312446],"study_design_scores_gemma":[0.00009681984,0.0007088725,0.01648404,0.00004846246,0.00008903382,0.0004625756,0.0004256927,0.8230202,0.1426372,0.006653064,0.009323286,0.00005087073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3684148,0.0004945173,0.6083221,0.0004163892,0.0002560072,0.0002081536,0.000502599,0.01017445,0.01121092],"genre_scores_gemma":[0.8227377,0.0001157964,0.1643509,0.000213601,0.00004805924,0.0001174518,0.001025349,0.0002558506,0.01113524],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00537319,"threshold_uncertainty_score":0.01797509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01889662155245932,"score_gpt":0.2883796717198865,"score_spread":0.2694830501674272,"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."}}