{"id":"W4312526008","doi":"10.1109/cvpr52688.2022.00888","title":"Few-shot Learning with Noisy Labels","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Machine learning; Transformer; Single shot; Pattern recognition (psychology); 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006500356,0.0003950275,0.0004004027,0.0003866278,0.001048584,0.0007645344,0.0006654842,0.00008142309,0.001981366],"category_scores_gemma":[0.00001391173,0.0003648923,0.00009671592,0.0005752139,0.00008109806,0.0005631343,0.0004540185,0.001027507,0.0003369311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006853503,"about_ca_system_score_gemma":0.00009865465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002957527,"about_ca_topic_score_gemma":0.00001498259,"domain_scores_codex":[0.9964506,0.0007015993,0.0004392666,0.001020862,0.0008926152,0.0004950482],"domain_scores_gemma":[0.9985073,0.000256383,0.0003115951,0.0004369309,0.0002118621,0.0002758783],"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":[0.0001112817,0.0002560168,0.0009862018,0.00003712106,0.00004967866,0.0001645961,0.002030018,0.001672004,0.0009072128,0.001152048,0.002501554,0.9901323],"study_design_scores_gemma":[0.004594528,0.005963868,0.00682011,0.0003736034,0.00003907379,0.0004952846,0.0009638573,0.9189445,0.0006865354,0.001738309,0.0576501,0.001730229],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1586089,0.000050361,0.8297245,0.002733047,0.001348955,0.0005030298,0.00003231519,0.0005588182,0.006440071],"genre_scores_gemma":[0.9862994,0.0000834176,0.006411846,0.005642562,0.0001719261,0.0001056086,0.0001307786,0.00004090289,0.001113588],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.988402,"threshold_uncertainty_score":0.9998803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05155474951415761,"score_gpt":0.2671397154031331,"score_spread":0.2155849658889755,"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."}}