{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002529867,0.001970264,0.002318207,0.002098132,0.0007712976,0.002010635,0.005098833,0.002843153,0.002088369],"category_scores_gemma":[0.00938057,0.0005577424,0.001280902,0.001265879,0.001232977,0.005106893,0.002609235,0.00316415,0.001934074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001189349,"about_ca_system_score_gemma":0.0008349204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003237468,"about_ca_topic_score_gemma":0.005125457,"domain_scores_codex":[0.9975967,0.0005428247,0.0001076456,0.0009744212,0.0005882473,0.0001903059],"domain_scores_gemma":[0.9953257,0.001744102,0.0003000393,0.001269004,0.0011073,0.0002538102],"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":[0.0006823106,0.001320902,0.005821334,0.0004779171,0.0002796282,0.0002709425,0.0003338748,0.1147125,0.03978612,0.003540447,0.01175212,0.821022],"study_design_scores_gemma":[0.00002456047,0.0002061861,0.0008616596,0.00003105655,0.00003918125,0.0001394154,0.00009591743,0.9710161,0.01821773,0.007957051,0.001380315,0.00003072812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1313237,0.001822592,0.8506641,0.0004731834,0.0002851307,0.0002733451,0.0006375886,0.01035958,0.004160783],"genre_scores_gemma":[0.6592948,0.0003416002,0.3297825,0.0006827156,0.0001614902,0.0002223242,0.003756537,0.0005357662,0.005222179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005098833,"threshold_uncertainty_score":0.0133794,"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."}}