{"id":"W3036461888","doi":"","title":"Improving Few-Shot Visual Classification with Unlabelled Examples","year":2021,"lang":"en","type":"article","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":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Mahalanobis distance; Machine learning; Feature (linguistics); Cluster analysis; Shot (pellet); Test set; Training set; Set (abstract data type); One shot","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":[],"consensus_categories":[],"category_scores_codex":[0.000169558,0.0001405952,0.0001370864,0.0001151054,0.0002715375,0.0001595673,0.0004250195,0.00006263042,0.00007766749],"category_scores_gemma":[0.00005146167,0.000148233,0.00005371874,0.001023174,0.00006609248,0.0006531502,0.0001708785,0.0001673025,0.0001097262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008505451,"about_ca_system_score_gemma":0.0001979233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003494413,"about_ca_topic_score_gemma":0.0000532285,"domain_scores_codex":[0.998745,0.000137271,0.0001224608,0.0006252051,0.0001044387,0.0002656225],"domain_scores_gemma":[0.9989734,0.0001216043,0.000128531,0.0004480377,0.0001935733,0.0001349094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007955336,0.0002558549,0.01211585,0.00003537252,0.00008592287,0.0007498625,0.001002675,0.02111084,0.02133482,0.9246218,0.0001408246,0.01846658],"study_design_scores_gemma":[0.00133601,0.0001208943,0.01319136,0.00002617697,0.00003064764,0.00002729764,0.001424253,0.9758949,0.00200849,0.001236,0.004304618,0.0003993142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2516973,0.00002266448,0.7426351,0.0001207689,0.00008900472,0.00006805768,5.591133e-7,0.0001812038,0.005185262],"genre_scores_gemma":[0.9887227,0.00001967854,0.007493402,0.0001828101,0.00002814656,5.036844e-7,0.000008992501,0.00001128368,0.003532502],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9547841,"threshold_uncertainty_score":0.6044766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09894198425784734,"score_gpt":0.199139770074696,"score_spread":0.1001977858168487,"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."}}