{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008604595,0.0002510686,0.000291437,0.0001958077,0.0002836394,0.0007168992,0.001199699,0.0002810661,0.00008185569],"category_scores_gemma":[0.0003087097,0.0002499716,0.0001780094,0.0001790718,0.00007920914,0.0003069838,0.0008044019,0.0006204952,0.0003962163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009233312,"about_ca_system_score_gemma":0.0001759365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000103602,"about_ca_topic_score_gemma":0.000002229105,"domain_scores_codex":[0.9979413,0.0001468467,0.0004083953,0.0008340437,0.0003212859,0.0003481412],"domain_scores_gemma":[0.9980939,0.0003164068,0.0003785635,0.0007242982,0.0003573,0.0001295127],"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":[0.00003510938,0.0001558715,0.005276638,0.0006512849,0.0003191904,0.000008161321,0.00499407,0.003085919,0.004090314,0.3824105,0.04840638,0.5505666],"study_design_scores_gemma":[0.0003916555,0.0001027032,0.009094473,0.00006484774,0.00002327744,0.000001902567,0.000135343,0.7699092,0.0005910891,0.0157226,0.203427,0.000535908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00119733,0.00002341751,0.9511229,0.001805721,0.0006966779,0.0004398074,0.000002731464,0.0006653285,0.04404606],"genre_scores_gemma":[0.4582576,0.00001603462,0.5297753,0.000305985,0.0007584344,0.0001480204,0.0001483357,0.00004030157,0.01055002],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7668233,"threshold_uncertainty_score":0.9999952,"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."}}