{"id":"W4402716033","doi":"10.1109/cvpr52733.2024.02706","title":"AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation","year":2024,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Adaptation (eye); Test (biology); Artificial intelligence","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":[0.0053975,0.002675365,0.001990212,0.002030966,0.001071165,0.002220113,0.004464831,0.002729602,0.003903776],"category_scores_gemma":[0.02786059,0.0008006105,0.001426865,0.001250744,0.001189062,0.0035957,0.003914877,0.005116476,0.00394757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001356628,"about_ca_system_score_gemma":0.00220138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008261872,"about_ca_topic_score_gemma":0.009533938,"domain_scores_codex":[0.9960572,0.001011808,0.0002772996,0.001275142,0.001079725,0.0002990005],"domain_scores_gemma":[0.9884012,0.004237333,0.0007845438,0.003004634,0.003155837,0.0004165592],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007014354,0.000479997,0.008374008,0.0004166387,0.0005050944,0.0001926921,0.000365968,0.1829711,0.0229804,0.006872524,0.03220632,0.7439338],"study_design_scores_gemma":[0.00004122563,0.0001153077,0.001664835,0.00003730529,0.00004387412,0.0001308063,0.00005315892,0.9758309,0.01147343,0.006659276,0.003896234,0.00005375031],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01510997,0.001033005,0.963748,0.0002768056,0.0003592873,0.0001816002,0.0005645652,0.01694198,0.00178475],"genre_scores_gemma":[0.3431523,0.0005800838,0.6392511,0.0008680727,0.0003186175,0.0006178209,0.004997019,0.003052054,0.007162803],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008261872,"threshold_uncertainty_score":0.02854502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03105031450111565,"score_gpt":0.292239587575416,"score_spread":0.2611892730743003,"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."}}