{"id":"W4403887899","doi":"10.1007/978-3-031-72949-2_7","title":"Adapt Without Forgetting: Distill Proximity from Dual Teachers in Vision-Language Models","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Forgetting; Dual (grammatical number); Artificial intelligence; Human–computer interaction; Computer vision; Natural language processing; Computer graphics (images); Cognitive science; Cognitive psychology; Linguistics; 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":[0.001077927,0.001197237,0.001543476,0.0009029231,0.0005633571,0.001263562,0.002578453,0.002284538,0.002989102],"category_scores_gemma":[0.004306933,0.0008170553,0.001127048,0.001022554,0.000671179,0.00344706,0.003268754,0.003453323,0.001657474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007133911,"about_ca_system_score_gemma":0.001063308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009232092,"about_ca_topic_score_gemma":0.01359207,"domain_scores_codex":[0.9991179,0.0001801864,0.00003040431,0.0004427138,0.0001084107,0.0001204084],"domain_scores_gemma":[0.9987592,0.0006833407,0.0000661131,0.0002267456,0.0001456031,0.0001190387],"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":[0.001001683,0.0004371642,0.002602167,0.0002134399,0.0001930649,0.0002373612,0.0004569775,0.1649893,0.01146399,0.006075841,0.007796849,0.8045322],"study_design_scores_gemma":[0.00002486286,0.0001070335,0.0004051668,0.00001954871,0.00003780328,0.00006605578,0.00006126378,0.985113,0.00372254,0.009553115,0.0008725672,0.00001696469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06531645,0.001468014,0.9263698,0.0004083244,0.0001949585,0.000074102,0.0003446231,0.003482147,0.002341628],"genre_scores_gemma":[0.742251,0.000626575,0.2451952,0.0005460202,0.0001820384,0.0001360036,0.00155811,0.0005876771,0.008917452],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009232092,"threshold_uncertainty_score":0.01835674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0192529939868261,"score_gpt":0.2673125237435382,"score_spread":0.2480595297567121,"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."}}