{"id":"W3127129507","doi":"","title":"Incremental few-shot learning via vector quantization in deep embedded space","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Forgetting; Overfitting; Learning vector quantization; Computer science; Artificial intelligence; Regularization (linguistics); Machine learning; Quantization (signal processing); Incremental learning; Support vector machine; Deep learning; Reproducing kernel Hilbert space; Vector quantization; Kernel (algebra); Pattern recognition (psychology); Artificial neural network; Algorithm; Mathematics; Hilbert space","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":[0.001072807,0.0008815868,0.001440251,0.0005369193,0.0003608342,0.0008113087,0.002234479,0.0009061279,0.00125835],"category_scores_gemma":[0.003851192,0.0004898931,0.0006238614,0.0007715303,0.0007881862,0.003015114,0.001505671,0.002285868,0.000444524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008207439,"about_ca_system_score_gemma":0.001013237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005951458,"about_ca_topic_score_gemma":0.006709753,"domain_scores_codex":[0.9992711,0.0001570234,0.00004949713,0.0002525946,0.0001986632,0.00007104113],"domain_scores_gemma":[0.9988961,0.0004465177,0.0001051631,0.0002612373,0.0002165005,0.00007449376],"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":[0.0002619131,0.0002556368,0.001912587,0.0002315489,0.0001039738,0.0001240938,0.000273943,0.3360319,0.01128077,0.01153349,0.004496409,0.6334937],"study_design_scores_gemma":[0.000008873083,0.00004655477,0.0001761609,0.000006826229,0.000008240751,0.00002467963,0.00001470113,0.99152,0.001998555,0.0057703,0.0004151073,0.00001003023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02441413,0.000729829,0.972958,0.0001401852,0.00007408906,0.00005554373,0.00009673068,0.001063061,0.0004684974],"genre_scores_gemma":[0.7403956,0.0006944091,0.2540973,0.0003156634,0.0001032527,0.000193772,0.0008867008,0.0001598001,0.003153478],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005951458,"threshold_uncertainty_score":0.01183367,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05821540092947535,"score_gpt":0.3431383331195025,"score_spread":0.2849229321900272,"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."}}