{"id":"W4393147203","doi":"10.1609/aaai.v38i15.29573","title":"Leveraging Normalization Layer in Adapters with Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learning","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology","keywords":"Normalization (sociology); Computer science; Distillation; Shot (pellet); Layer (electronics); Artificial intelligence; Materials science; Chemistry; Chromatography; Nanotechnology","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":[0.0007182416,0.0002154584,0.000211418,0.0002289147,0.0003187327,0.0007754025,0.000403526,0.00007402282,0.00001591054],"category_scores_gemma":[0.0003006869,0.0001660738,0.00005596604,0.0007009558,0.0002131998,0.0007972748,0.0001417798,0.0004337142,0.000007224325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000712175,"about_ca_system_score_gemma":0.00009161367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001652136,"about_ca_topic_score_gemma":0.000007929715,"domain_scores_codex":[0.9983033,0.00003948271,0.0004102109,0.0005558287,0.0003715713,0.0003196218],"domain_scores_gemma":[0.9989535,0.0002157865,0.0002758433,0.00008413303,0.0004058965,0.00006490239],"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":[0.0002985888,0.00004466501,0.006745611,0.0001509352,0.00002873969,0.000003584723,0.01738469,0.01410997,0.008995055,0.8445281,0.00000606745,0.107704],"study_design_scores_gemma":[0.00009853669,0.0004458514,0.001377059,0.000918009,0.00001125057,0.00001253126,0.004640845,0.9467705,0.01924769,0.02577233,0.0004065478,0.0002987955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3492427,0.0001334653,0.6446182,0.001036468,0.0002096594,0.0007725034,0.000001422227,0.0001900174,0.003795508],"genre_scores_gemma":[0.9911271,0.00001905246,0.008433295,0.000041686,0.0000411945,0.00006206129,0.000001737757,0.00002051332,0.0002533945],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9326606,"threshold_uncertainty_score":0.7477224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07970498633852996,"score_gpt":0.326450864721229,"score_spread":0.2467458783826991,"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."}}