{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000997298,0.0003200754,0.000438674,0.000349094,0.0001272124,0.0009725888,0.001106422,0.0003514172,0.000279063],"category_scores_gemma":[0.0004500739,0.0003357784,0.0001748237,0.0005356554,0.00005121862,0.0003885111,0.001264813,0.00166672,0.0001122568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002279087,"about_ca_system_score_gemma":0.0007862648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003664982,"about_ca_topic_score_gemma":0.0002159317,"domain_scores_codex":[0.996877,0.0005164813,0.0005923053,0.00105023,0.0005567939,0.0004071705],"domain_scores_gemma":[0.9984249,0.0001685779,0.0002949449,0.0007653438,0.0002137115,0.0001325097],"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":[0.00003470324,0.0003679676,0.007434539,0.00024015,0.0001299342,0.0002569923,0.02235434,0.0494212,0.003415285,0.2937118,0.0009944065,0.6216387],"study_design_scores_gemma":[0.0009110898,0.00007815623,0.08732677,0.0002988765,0.00001231675,0.000024987,0.004750861,0.8836673,0.0005408018,0.001448103,0.01994494,0.0009957368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02494269,0.0002839625,0.858086,0.001842824,0.001051445,0.0003212117,8.163635e-7,0.0006107558,0.1128603],"genre_scores_gemma":[0.9535044,0.00008198385,0.04168482,0.0005786112,0.00008915095,0.00006256373,0.00007539165,0.00002368631,0.00389942],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9285617,"threshold_uncertainty_score":0.9999094,"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."}}