{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008080996,0.0002405094,0.0002350688,0.0001252055,0.0002791671,0.0008255924,0.001407804,0.0001102889,0.00004838694],"category_scores_gemma":[0.0002034708,0.0001905976,0.0001157772,0.0008980855,0.0001178828,0.0005504979,0.000243005,0.0003459693,0.0003955498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006845931,"about_ca_system_score_gemma":0.0001181321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003197268,"about_ca_topic_score_gemma":0.000002048075,"domain_scores_codex":[0.9978836,0.00004225333,0.0005752349,0.0005581768,0.0005911359,0.0003496389],"domain_scores_gemma":[0.998745,0.0002284597,0.0002752171,0.000206709,0.0004608808,0.00008369694],"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":[0.00003408288,0.0001447141,0.0002387289,0.0002014573,0.00003616965,0.000002495826,0.008041903,0.002973065,0.1086986,0.8324749,0.002761207,0.04439264],"study_design_scores_gemma":[0.00002759457,0.0002478236,0.00005077709,0.0006242594,0.00001028805,0.00001295735,0.0008494949,0.8578491,0.06479067,0.07130422,0.003908966,0.000323829],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06957153,0.0001007398,0.9147053,0.004062675,0.0008216185,0.0004926235,0.0000227784,0.0005704297,0.009652277],"genre_scores_gemma":[0.9968318,0.00001712635,0.001963859,0.00008334813,0.00009917829,0.00001873275,0.000007665409,0.00001670753,0.0009616355],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9272602,"threshold_uncertainty_score":0.7961206,"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."}}