{"id":"W4294969213","doi":"10.1609/aaai.v35i11.17171","title":"`Less Than One'-Shot Learning: Learning N Classes From M < N Samples","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Shot (pellet); Class (philosophy); Artificial intelligence; Task (project management); Computer science; Machine learning; Training (meteorology); One shot; Artificial neural network; Engineering","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":[0.002658575,0.001543953,0.002812312,0.0006768897,0.00112813,0.001409648,0.005295047,0.003703924,0.00387794],"category_scores_gemma":[0.007549838,0.0009148931,0.001279552,0.000948113,0.002288158,0.006180837,0.00368573,0.003837192,0.001068652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001308956,"about_ca_system_score_gemma":0.001441207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006208773,"about_ca_topic_score_gemma":0.007438927,"domain_scores_codex":[0.9985952,0.0003779564,0.00008200067,0.0005938585,0.0002104788,0.0001405588],"domain_scores_gemma":[0.9966299,0.001628301,0.0002226087,0.0009176914,0.0003064638,0.0002950225],"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":[0.001272928,0.001173062,0.00528868,0.0006323374,0.0004113495,0.0004504682,0.0006406671,0.2019941,0.01572202,0.02353488,0.01885439,0.7300252],"study_design_scores_gemma":[0.00005948194,0.0002286155,0.0007932876,0.00002712375,0.00004525561,0.0001770878,0.00009465005,0.9408795,0.006354159,0.04919506,0.002100868,0.00004487209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04144813,0.0005326082,0.9527136,0.000996668,0.0001574196,0.0002945982,0.0002596044,0.001950413,0.001646985],"genre_scores_gemma":[0.5362425,0.0003696606,0.4515408,0.001657051,0.0003491991,0.0004890393,0.0016647,0.0002863924,0.007400558],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006208773,"threshold_uncertainty_score":0.01406008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2065969663041616,"score_gpt":0.315659843378008,"score_spread":0.1090628770738465,"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."}}