{"id":"W4386076614","doi":"10.1109/cvpr52729.2023.01147","title":"EcoTTA: Memory-Efficient Continual Test-Time Adaptation via Self-Distilled Regularization","year":2023,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Forgetting; Computer science; Regularization (linguistics); 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":[0.00103738,0.001403628,0.000909221,0.000685093,0.0004098412,0.0007612696,0.003050821,0.001412342,0.002801806],"category_scores_gemma":[0.004325382,0.0005200342,0.0007361128,0.0005421979,0.0008343279,0.00197245,0.001799953,0.002284795,0.001204113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006573265,"about_ca_system_score_gemma":0.001164291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004897312,"about_ca_topic_score_gemma":0.007825724,"domain_scores_codex":[0.9995715,0.00008058181,0.00002639523,0.0001307497,0.000128729,0.00006201947],"domain_scores_gemma":[0.9988262,0.0004184619,0.00009487969,0.0002898109,0.0002889976,0.00008167463],"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":[0.0003419822,0.0004335948,0.002225511,0.0001627364,0.0001904751,0.0002233166,0.0002092672,0.3640243,0.03956715,0.006635102,0.01083507,0.5751514],"study_design_scores_gemma":[0.00001629547,0.00005560201,0.0002071772,0.000008357536,0.00001653495,0.0000435053,0.00001183151,0.991983,0.004590497,0.001921841,0.001132528,0.00001277358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03832414,0.0006584409,0.949752,0.0002377154,0.0002075975,0.0001260197,0.0001107935,0.007576481,0.003006661],"genre_scores_gemma":[0.6509347,0.000309933,0.3365427,0.0006239816,0.0001461615,0.0003726876,0.0006825149,0.001070533,0.009316776],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004897312,"threshold_uncertainty_score":0.00973767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009933171051921366,"score_gpt":0.2172954586590134,"score_spread":0.207362287607092,"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."}}