{"id":"W3118334164","doi":"10.1109/wacv48630.2021.00332","title":"Towards Contextual Learning in Few-shot Object Classification","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Leverage (statistics); Computer science; Artificial intelligence; Isolation (microbiology); Object (grammar); Context (archaeology); Visual Objects; Machine learning; Perception; Psychology","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":[0.002090129,0.001442489,0.002111949,0.001996387,0.000790911,0.001546235,0.003000003,0.002362807,0.002081742],"category_scores_gemma":[0.006841946,0.0008149674,0.001276911,0.001376375,0.001678601,0.00332627,0.002992479,0.002794935,0.0008677374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001146025,"about_ca_system_score_gemma":0.0009416267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004244226,"about_ca_topic_score_gemma":0.006102951,"domain_scores_codex":[0.9986118,0.000350689,0.00005381929,0.0006011579,0.0002411645,0.0001413262],"domain_scores_gemma":[0.9975129,0.001381422,0.0001651691,0.0004839611,0.0002736467,0.0001828921],"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":[0.0004622866,0.000534157,0.004698211,0.0005432189,0.0002594116,0.0002576372,0.0004977966,0.2723021,0.01948868,0.02494643,0.006843245,0.6691668],"study_design_scores_gemma":[0.00001841189,0.000067295,0.0005900884,0.00002529094,0.00002399574,0.0000558354,0.00004980673,0.9637324,0.004028625,0.030091,0.001300649,0.00001649903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01968076,0.0008087227,0.9766896,0.0002529682,0.00004400622,0.0000610798,0.0001103348,0.001657547,0.0006949203],"genre_scores_gemma":[0.4917739,0.0007243435,0.5022665,0.0008035089,0.0003310934,0.0002334644,0.001237206,0.0003393256,0.002290777],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004244226,"threshold_uncertainty_score":0.0110538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0804871400187697,"score_gpt":0.3115426588140197,"score_spread":0.2310555187952499,"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."}}