{"id":"W2963031676","doi":"10.1109/cvpr.2018.00575","title":"Between-Class Learning for Image Classification","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":190,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Core Research for Evolutional Science and Technology; Canadian Institute for Advanced Research","keywords":"Mixing (physics); Generalization; Computer science; Image (mathematics); Convolutional neural network; Artificial intelligence; Contextual image classification; Pattern recognition (psychology); Class (philosophy); Feature (linguistics); Feature extraction; Generalization error; Deep learning; Artificial neural network; Machine learning; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003450257,0.002197789,0.001973031,0.002351098,0.001066831,0.002091989,0.005047004,0.002898306,0.00752259],"category_scores_gemma":[0.009507238,0.0005975136,0.001647314,0.002400659,0.001836408,0.005719485,0.002962484,0.005307697,0.004609918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001769773,"about_ca_system_score_gemma":0.001177804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003466723,"about_ca_topic_score_gemma":0.002845068,"domain_scores_codex":[0.9957877,0.001122872,0.0001764243,0.001359461,0.001310125,0.0002433632],"domain_scores_gemma":[0.9955223,0.00179067,0.0003054702,0.001433971,0.0007692677,0.0001783332],"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":[0.0002336206,0.0003225988,0.001206463,0.0003591328,0.0002147511,0.00009418607,0.00008576753,0.05564457,0.006501682,0.04016242,0.01829465,0.87688],"study_design_scores_gemma":[0.00002661436,0.00008580176,0.000463572,0.00004051644,0.00003531406,0.0001467789,0.00003416876,0.8927745,0.008262189,0.0865112,0.01158543,0.00003401248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004227438,0.001633884,0.9878076,0.0005430959,0.000265146,0.0001056718,0.0002242392,0.001890242,0.003302678],"genre_scores_gemma":[0.2533928,0.001576851,0.7310959,0.001104254,0.0009395072,0.0005195829,0.002176338,0.000583808,0.008611016],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00752259,"threshold_uncertainty_score":0.02516556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07627495516437881,"score_gpt":0.3249330674113987,"score_spread":0.2486581122470199,"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."}}