{"id":"W4385327582","doi":"10.48550/arxiv.2307.13755","title":"Training-based Model Refinement and Representation Disagreement for Semi-Supervised Object Detection","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; fRI Research","keywords":"Overfitting; Computer science; Pascal (unit); Artificial intelligence; Margin (machine learning); Machine learning; Representation (politics); Object (grammar); Generalization; Pattern recognition (psychology); Artificial neural network; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005263895,0.002091462,0.00223668,0.001330961,0.0008951319,0.001269706,0.004972028,0.002289129,0.001653278],"category_scores_gemma":[0.01420879,0.001185488,0.001732742,0.001112801,0.001658309,0.00300359,0.003454985,0.004049416,0.001213512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001139677,"about_ca_system_score_gemma":0.001768046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00431309,"about_ca_topic_score_gemma":0.004729711,"domain_scores_codex":[0.9959643,0.001421853,0.0001941745,0.001218936,0.0009269866,0.0002737307],"domain_scores_gemma":[0.9928929,0.003475482,0.000621283,0.00152557,0.001246917,0.0002378534],"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":[0.0004030126,0.0002496637,0.002596046,0.0002178141,0.0002143501,0.0001829541,0.0005021005,0.4678355,0.01989607,0.009710469,0.004590987,0.493601],"study_design_scores_gemma":[0.000009244241,0.00004175623,0.0001493579,0.000006070615,0.000009934775,0.00004063798,0.00001946051,0.9922606,0.003776994,0.003140742,0.0005342697,0.00001082379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01044089,0.0001814007,0.9875548,0.0000964482,0.00002480988,0.00003460196,0.00002634206,0.001292149,0.0003484497],"genre_scores_gemma":[0.5109116,0.0002445051,0.4831533,0.0004989166,0.0001264078,0.0002099043,0.0007235584,0.0005373024,0.003594578],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005263895,"threshold_uncertainty_score":0.02783847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2137014394924574,"score_gpt":0.2541779916524084,"score_spread":0.04047655215995097,"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."}}