{"id":"W4415280187","doi":"10.1109/tpami.2025.3621631","title":"Vicinal Gaussian Transform: Rethinking Source-Free Domain Adaptation Through Source-Informed Label Consistency","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Vicinal; Covariance; Gaussian; Domain (mathematical analysis); Smoothness; Divergence (linguistics); Gaussian process; Wavelet transform","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":[0.001747416,0.0009905499,0.0008384518,0.0007178981,0.000433598,0.001306446,0.002111637,0.001299434,0.001781007],"category_scores_gemma":[0.006223,0.0003820474,0.0008840165,0.000883231,0.001420544,0.002700589,0.003120287,0.003136116,0.001347788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006199114,"about_ca_system_score_gemma":0.001208562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002646212,"about_ca_topic_score_gemma":0.003614663,"domain_scores_codex":[0.9992926,0.0001860183,0.00003172268,0.0002092158,0.0002193556,0.00006113558],"domain_scores_gemma":[0.9983603,0.000504757,0.0001172026,0.0005996568,0.0003257689,0.00009224432],"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":[0.0002733989,0.0001864422,0.002422161,0.0001859256,0.0001454417,0.0001690656,0.0004515001,0.3847788,0.04709449,0.04448121,0.0081787,0.5116329],"study_design_scores_gemma":[0.00001224774,0.00003303674,0.0001849252,0.00001465989,0.000009417401,0.00005700811,0.00003264378,0.9695836,0.007567859,0.02006339,0.002424516,0.00001681012],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008926727,0.0001463394,0.9890476,0.0001286936,0.00004680724,0.00001830555,0.00005750414,0.0009691016,0.0006589425],"genre_scores_gemma":[0.3547856,0.0004487262,0.6377824,0.0005689351,0.0001108862,0.0001240222,0.0008693673,0.001197555,0.004112634],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002646212,"threshold_uncertainty_score":0.009241343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02967903218956129,"score_gpt":0.2877978970288453,"score_spread":0.258118864839284,"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."}}