{"id":"W3204478713","doi":"10.48550/arxiv.2011.11872","title":"Mixture-based Feature Space Learning for Few-shot Image Classification","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Compute Canada","keywords":"Pattern recognition (psychology); Artificial intelligence; Feature learning; Feature (linguistics); Computer science; Discriminative model; Feature vector; Mixture model; Cluster analysis; Context (archaeology); Feature extraction; Representation (politics); Extractor; Contextual image classification; Machine learning; Image (mathematics); Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001399495,0.001522266,0.001895759,0.002021352,0.0005708884,0.001171924,0.00318146,0.001444191,0.003114406],"category_scores_gemma":[0.004132794,0.0004902619,0.001496727,0.001815482,0.0008278594,0.003042943,0.00216304,0.00279557,0.00229609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000988854,"about_ca_system_score_gemma":0.000700802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00400972,"about_ca_topic_score_gemma":0.003786956,"domain_scores_codex":[0.998879,0.0002368454,0.00005211529,0.0004018043,0.0002699263,0.0001602595],"domain_scores_gemma":[0.9989138,0.0003792575,0.000114474,0.0002612195,0.0002475321,0.00008373246],"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":[0.0003600394,0.0003598667,0.003232735,0.0001967832,0.0002012253,0.0001456416,0.0001981179,0.1746461,0.01798755,0.01190186,0.008469686,0.7823005],"study_design_scores_gemma":[0.000008145495,0.00005735623,0.0003922199,0.00001110555,0.00001473494,0.00006683023,0.00001858072,0.9828892,0.004531276,0.01087841,0.001115089,0.00001712286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008796164,0.0004204264,0.987844,0.00008702739,0.00003596123,0.00004505437,0.0001836539,0.002147655,0.0004400962],"genre_scores_gemma":[0.4689552,0.0005482291,0.5234262,0.0002914394,0.0001744649,0.0003287592,0.002784188,0.0003260902,0.003165459],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00400972,"threshold_uncertainty_score":0.01041871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09941407703492308,"score_gpt":0.2029778504973191,"score_spread":0.103563773462396,"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."}}