{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001604613,0.0001127191,0.00009564783,0.0001129747,0.00008706724,0.000410561,0.0002768144,0.00003054753,0.00009032669],"category_scores_gemma":[0.00001392539,0.00008169299,0.00003857883,0.0006948296,0.00003068693,0.0004916001,0.00009538668,0.0001558593,0.0006985179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004792496,"about_ca_system_score_gemma":0.00009537723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009757209,"about_ca_topic_score_gemma":0.00001735949,"domain_scores_codex":[0.9991196,0.00005303206,0.0001081743,0.0003592703,0.0001367844,0.000223098],"domain_scores_gemma":[0.999513,0.000137976,0.00001925973,0.000207609,0.00004879627,0.00007330751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002254153,0.00009248948,0.001056973,0.00006377117,0.0001861415,0.000253997,0.007929244,0.001852351,0.0009663588,0.5373388,0.01164004,0.4385973],"study_design_scores_gemma":[0.0002410623,0.00009826617,0.001164006,0.00004461859,0.000009957188,0.00009354741,0.0000676807,0.7966185,0.001578351,0.002502085,0.1972774,0.0003044686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009681628,0.0003533885,0.94683,0.0004393655,0.0002512442,0.00007345954,2.925167e-7,0.0004732121,0.04189735],"genre_scores_gemma":[0.8983376,0.00001161367,0.09604878,0.0005122387,0.00005498646,0.00001128037,0.000001164693,0.00001299631,0.005009339],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.888656,"threshold_uncertainty_score":0.8978267,"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."}}