{"id":"W4382141764","doi":"10.48550/arxiv.2306.13275","title":"On The Relationship Between Continual Learning and Long-Tailed Recognition","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"MNIST database; Computer science; Artificial intelligence; Set (abstract data type); Machine learning; Forgetting; Context (archaeology); Function (biology); Pattern recognition (psychology); Deep learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007073749,0.0001955399,0.0001899764,0.0002377675,0.0004449916,0.0002330646,0.0005642721,0.0002032379,0.0000293875],"category_scores_gemma":[0.0008422561,0.0001897004,0.00009502461,0.0004883963,0.00009557569,0.0002119923,0.0007035558,0.00114253,0.0004548698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007194494,"about_ca_system_score_gemma":0.00006259487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002118208,"about_ca_topic_score_gemma":0.00001733373,"domain_scores_codex":[0.9983203,0.0004819044,0.000167708,0.0006923921,0.0001100482,0.0002275835],"domain_scores_gemma":[0.9964039,0.00276632,0.0002522776,0.0003833547,0.0000930094,0.000101189],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003306448,0.00002740618,0.6281591,0.00005352499,0.0001026126,0.0001452666,0.001290402,0.0311212,0.000003235166,0.3344317,0.0003542007,0.004278302],"study_design_scores_gemma":[0.0007630925,0.0001183095,0.5864937,0.000337313,0.00008682985,0.000002914056,0.0005801974,0.1557916,0.00000934259,0.2546964,0.0004961682,0.0006241852],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6099906,0.00001128946,0.3867284,0.0004732093,0.0002111429,0.0002181752,0.000004583559,0.0003682745,0.001994286],"genre_scores_gemma":[0.9932229,0.00002789162,0.0002993902,0.00007438866,0.00006335085,0.000001561275,0.00004236537,0.00001795982,0.006250189],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.386429,"threshold_uncertainty_score":0.7735758,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2225420793896809,"score_gpt":0.2300947928023223,"score_spread":0.007552713412641354,"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."}}