{"id":"W3015943301","doi":"10.1109/ijcnn48605.2020.9206833","title":"Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks","year":2020,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Linear discriminant analysis; MNIST database; Pattern recognition (psychology); Discriminant; Artificial intelligence; Subspace topology; Computer science; Metric (unit); Artificial neural network; Feature (linguistics); Kernel Fisher discriminant analysis; Multiple discriminant analysis; Feature extraction; Fisher kernel; Mathematics; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.00009137542,0.00008884262,0.0001313678,0.00001574421,0.00008076019,0.0001167918,0.0001840742,0.00003780533,0.00001164012],"category_scores_gemma":[0.00006665813,0.00007246559,0.00003292014,0.0001312276,0.0000397382,0.0003147944,0.00007015228,0.00007031456,0.000001306563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001758551,"about_ca_system_score_gemma":0.00002904123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001191663,"about_ca_topic_score_gemma":0.00001819565,"domain_scores_codex":[0.9992928,0.00001838203,0.0001198978,0.0002986196,0.00007819886,0.0001920876],"domain_scores_gemma":[0.9995573,0.0001699181,0.00004246174,0.0001011411,0.00003394665,0.00009525038],"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":[0.000176624,0.00002823328,0.0004493547,0.00006026985,0.00006760177,0.00001359051,0.01200039,0.001835641,0.0007060671,0.02894453,0.02740597,0.9283118],"study_design_scores_gemma":[0.0006717168,0.0003481904,0.0009290822,0.00001187778,0.00001010305,0.000007224382,0.0004890386,0.9845156,0.0006310291,0.001086668,0.01114516,0.0001543088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001798092,0.0001191429,0.9900265,0.006498532,0.000252785,0.0002363079,0.000002219289,0.0001234683,0.0009429291],"genre_scores_gemma":[0.9735511,0.0000164511,0.02376711,0.002271698,0.00022891,0.0000409627,8.38178e-7,0.000008056627,0.0001148773],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.98268,"threshold_uncertainty_score":0.2955061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05824717489090631,"score_gpt":0.2528135293446994,"score_spread":0.1945663544537931,"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."}}