{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01041611,0.001454726,0.001423451,0.001439153,0.001336787,0.002522018,0.003043473,0.002644046,0.002328404],"category_scores_gemma":[0.04592535,0.0009343922,0.0006982213,0.001266636,0.006941895,0.009393242,0.006338798,0.006777653,0.0007735596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002111369,"about_ca_system_score_gemma":0.001689017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002840544,"about_ca_topic_score_gemma":0.002847087,"domain_scores_codex":[0.9968663,0.001126844,0.0001401806,0.001171377,0.0004947575,0.0002004899],"domain_scores_gemma":[0.9623926,0.02809336,0.001947672,0.004318126,0.002099951,0.001148244],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006693529,0.0004187561,0.01610698,0.0005049913,0.0002227219,0.0003609268,0.00104406,0.4553261,0.006964545,0.2559466,0.008413949,0.2540211],"study_design_scores_gemma":[0.00002013876,0.0001521264,0.001247259,0.00004994054,0.00001864551,0.0001332198,0.00007753391,0.816624,0.001808599,0.1788048,0.001030578,0.00003310351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0447838,0.002231499,0.9461417,0.00253797,0.00009276831,0.00006788181,0.0001124574,0.0007745913,0.003257316],"genre_scores_gemma":[0.8402488,0.001897028,0.1504428,0.001553365,0.0004639761,0.0002662412,0.0004393872,0.0003264246,0.00436203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01041611,"threshold_uncertainty_score":0.05508631,"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."}}