{"id":"W4386243195","doi":"10.1109/crv60082.2023.00045","title":"Fast Fine-Tuning Using Curriculum Domain Adaptation","year":2023,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Fine-tuning; Domain (mathematical analysis); Artificial intelligence; Adaptation (eye); Artificial neural network; Domain adaptation; Machine learning; Enhanced Data Rates for GSM Evolution; Deep learning; Deep neural networks; Train; Training set; 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":[0.0008627442,0.001298409,0.001048917,0.0007377748,0.0004676351,0.0005919179,0.001901123,0.0008636609,0.002719881],"category_scores_gemma":[0.003441012,0.000511188,0.0008319987,0.0008453808,0.0005221741,0.002044383,0.001864403,0.002331322,0.001623274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007624635,"about_ca_system_score_gemma":0.001403446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004560567,"about_ca_topic_score_gemma":0.008919035,"domain_scores_codex":[0.9995085,0.00007954273,0.00003067078,0.0002090402,0.0001072247,0.00006504494],"domain_scores_gemma":[0.999177,0.0002058653,0.00006412656,0.0002548754,0.0002416048,0.00005652854],"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":[0.0002031797,0.0004737405,0.00357453,0.0002087714,0.0001257324,0.0001562855,0.000136892,0.2829366,0.04277204,0.006284642,0.0162475,0.64688],"study_design_scores_gemma":[0.00003568304,0.00006754991,0.0005515792,0.00001447897,0.00001846724,0.0000699871,0.00002800529,0.9802685,0.01046328,0.005246891,0.003218489,0.00001706518],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05850979,0.0007562313,0.9283625,0.0001904607,0.000196905,0.0001725991,0.0002892457,0.007639254,0.003882918],"genre_scores_gemma":[0.5473087,0.0006107605,0.4403591,0.0006649315,0.000109631,0.0004350899,0.002432246,0.0007460897,0.007333444],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004560567,"threshold_uncertainty_score":0.009098887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04296787530832765,"score_gpt":0.2791595648111833,"score_spread":0.2361916895028557,"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."}}