{"id":"W3118952246","doi":"","title":"A Universal Representation Transformer Layer for Few-Shot Image Classification","year":2021,"lang":"en","type":"article","venue":"UTS ePRESS (University of Technology Sydney)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Leverage (statistics); Artificial intelligence; Weighting; Contextual image classification; Transformer; Feature extraction; Pattern recognition (psychology); Machine learning; Visualization; Representation (politics); Feature (linguistics); Data mining; Image (mathematics)","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":[0.001081283,0.001410188,0.001086539,0.001057356,0.0004930755,0.001306764,0.002570083,0.001449,0.005369147],"category_scores_gemma":[0.002807175,0.000409809,0.0013611,0.001027607,0.0007627996,0.003427061,0.00250052,0.00311543,0.00307305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001151479,"about_ca_system_score_gemma":0.001133633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006019985,"about_ca_topic_score_gemma":0.008844742,"domain_scores_codex":[0.9994913,0.00006334083,0.00002218567,0.0002338877,0.0001006231,0.00008857467],"domain_scores_gemma":[0.9994034,0.0001531233,0.00004097433,0.0002146793,0.0001289431,0.00005900917],"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":[0.0003282866,0.0005305586,0.002979559,0.0002497256,0.0002125271,0.0001543626,0.0001922894,0.0562545,0.03404271,0.01017093,0.02457917,0.8703054],"study_design_scores_gemma":[0.00001939251,0.0001145363,0.0006985446,0.00002884924,0.0000535993,0.0001307962,0.00005238944,0.9627022,0.02089936,0.01103454,0.004239108,0.00002678119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04310361,0.001284536,0.931675,0.0005035972,0.0002853452,0.0002095841,0.0009983033,0.01705432,0.004885598],"genre_scores_gemma":[0.573757,0.0009065193,0.4021429,0.001057589,0.0001939979,0.000373828,0.006008899,0.00068663,0.01487262],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006019985,"threshold_uncertainty_score":0.01796162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04486204740380463,"score_gpt":0.2692368662175408,"score_spread":0.2243748188137362,"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."}}