{"id":"W4402702975","doi":"10.1109/cvpr52733.2024.02270","title":"Overcoming Generic Knowledge Loss with Selective Parameter Update","year":2024,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science","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":[0.002209161,0.002045405,0.002101621,0.001031212,0.0006913715,0.001502334,0.003761981,0.002697623,0.003482786],"category_scores_gemma":[0.01374519,0.000874676,0.001087539,0.0009602857,0.001360605,0.004306939,0.003639687,0.003385501,0.001778823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001097786,"about_ca_system_score_gemma":0.001731654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005487362,"about_ca_topic_score_gemma":0.008665223,"domain_scores_codex":[0.998596,0.0003802195,0.00009686119,0.0004950553,0.0002659711,0.0001658256],"domain_scores_gemma":[0.9953075,0.002073931,0.0002763957,0.00173651,0.0004439762,0.0001615759],"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":[0.000435188,0.0003521855,0.002591309,0.0003170033,0.0002036818,0.0003152628,0.000286848,0.3827482,0.01063779,0.009529193,0.01533065,0.5772527],"study_design_scores_gemma":[0.00003253418,0.00005619071,0.000272703,0.00001815135,0.00002594517,0.00008861555,0.00003529603,0.9802855,0.003211286,0.01469256,0.001263266,0.00001794727],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05227155,0.001155571,0.9320368,0.000695524,0.0001534103,0.0001500668,0.0004302084,0.009461883,0.003645016],"genre_scores_gemma":[0.7641783,0.0004647862,0.2253969,0.001299024,0.0002013242,0.0002759263,0.001656377,0.0008046279,0.005722721],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005487362,"threshold_uncertainty_score":0.01168329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01906503757162171,"score_gpt":0.2608357847861564,"score_spread":0.2417707472145347,"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."}}