{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003797523,0.0001068393,0.00008994376,0.0001285811,0.0001277832,0.0005918278,0.0004600136,0.00004733067,0.00009138384],"category_scores_gemma":[0.001154489,0.00009650786,0.00004953787,0.0003740812,0.00001620417,0.001244027,0.00008899868,0.00008530305,0.0006737187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004122587,"about_ca_system_score_gemma":0.00009421656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008328679,"about_ca_topic_score_gemma":0.000003319464,"domain_scores_codex":[0.999025,0.0000269344,0.0002097289,0.0003215006,0.0002264711,0.0001902976],"domain_scores_gemma":[0.9981802,0.001282627,0.00004757932,0.0003373989,0.00008919244,0.00006304922],"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":[0.000005357051,0.0000337962,0.000003579603,0.00004993373,0.00001089065,0.00000441166,0.001166556,0.004213525,0.002522819,0.318141,0.02060542,0.6532427],"study_design_scores_gemma":[0.0003094613,0.0000763939,0.000102802,0.00002490657,0.000006421977,0.000006351896,0.0000345107,0.9588282,0.0006253585,0.01406632,0.02579024,0.0001290032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002750021,0.00009200766,0.9855244,0.005629634,0.0003290305,0.0002618598,0.000004776108,0.0008561314,0.007027192],"genre_scores_gemma":[0.165686,0.000006763989,0.8205968,0.0009676654,0.00009990313,0.00007031151,0.00002450153,0.00001858168,0.01252947],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9546147,"threshold_uncertainty_score":0.8659516,"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."}}