{"id":"W4394625847","doi":"10.1109/wacv57701.2024.00178","title":"MoP-CLIP: A Mixture of Prompt-Tuned CLIP Models for Domain Incremental Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Interpreting and Communication in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Domain (mathematical analysis); Artificial intelligence; Mathematics","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":[0.00191012,0.001394785,0.00123702,0.0009962465,0.0004444848,0.001080255,0.003189345,0.00142844,0.003087376],"category_scores_gemma":[0.006612411,0.0005955821,0.00105213,0.001053002,0.0007670822,0.002577142,0.002519757,0.003324592,0.00151147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008246845,"about_ca_system_score_gemma":0.001695711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003783378,"about_ca_topic_score_gemma":0.005821897,"domain_scores_codex":[0.9992998,0.000198324,0.00003180846,0.0002345768,0.0001590024,0.00007645239],"domain_scores_gemma":[0.9977185,0.001093422,0.0001115635,0.0003677783,0.0005060133,0.0002028294],"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":[0.0007439243,0.0005458235,0.006522673,0.0003533471,0.000178962,0.0004142204,0.0003731233,0.3215955,0.006792265,0.01458634,0.02721907,0.6206748],"study_design_scores_gemma":[0.00003357862,0.0001133058,0.0003403901,0.0000168952,0.00002623436,0.00006555442,0.00002311091,0.987184,0.001513701,0.007950436,0.0027165,0.00001631403],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02314139,0.001217104,0.9661698,0.0005452113,0.0002164932,0.000216482,0.0006431522,0.00561874,0.002231645],"genre_scores_gemma":[0.5822918,0.001383889,0.395928,0.002085296,0.0005773753,0.0008690013,0.004550922,0.0006272372,0.01168642],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003783378,"threshold_uncertainty_score":0.01032829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08727296041669232,"score_gpt":0.4636961642340465,"score_spread":0.3764232038173542,"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."}}