{"id":"W4393160582","doi":"10.1609/aaai.v38i14.29527","title":"Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalization","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Distributed and Parallel Computing Systems","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; University of Toronto","funders":"Fundamental Research Funds for the Central Universities; Natural Sciences and Engineering Research Council of Canada","keywords":"Domain adaptation; Normalization (sociology); Computer science; Adaptation (eye); Artificial intelligence; Time domain; Test (biology); Machine learning; Psychology; Biology; Neuroscience; Computer vision","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001446075,0.002124463,0.001582601,0.0009692338,0.0005754983,0.001157781,0.003313241,0.00155266,0.003903971],"category_scores_gemma":[0.004700453,0.0006877515,0.001521504,0.001042209,0.001165382,0.002770503,0.001938129,0.003255964,0.00360756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001289115,"about_ca_system_score_gemma":0.001529338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007465535,"about_ca_topic_score_gemma":0.008942564,"domain_scores_codex":[0.999095,0.0001559107,0.00003910154,0.0004402713,0.000165398,0.0001044028],"domain_scores_gemma":[0.9983311,0.0003996402,0.0001295144,0.0005660144,0.0004585324,0.0001152492],"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":[0.0005153857,0.0003664466,0.003561804,0.0001745584,0.0001823744,0.0002070258,0.0002060706,0.2705147,0.03515228,0.006181777,0.02030359,0.662634],"study_design_scores_gemma":[0.00002588267,0.00004054208,0.0005226288,0.00001067406,0.00002495761,0.00006111592,0.00003262685,0.9819317,0.008894244,0.006047552,0.002385497,0.00002272046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02352625,0.0004551522,0.9633352,0.0002125937,0.0001898044,0.0001288227,0.0003162997,0.009308472,0.002527492],"genre_scores_gemma":[0.4574613,0.000471259,0.5214952,0.001078215,0.0002707372,0.0004455799,0.004127497,0.00206621,0.01258392],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007465535,"threshold_uncertainty_score":0.01484418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03066118912347452,"score_gpt":0.2597627833747798,"score_spread":0.2291015942513052,"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."}}