{"id":"W2776460497","doi":"10.1109/iccv.2017.62","title":"DualNet: Learn Complementary Features for Image Recognition","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Youth Innovation Promotion Association; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Computer science; Subnetwork; Artificial intelligence; Extractor; Classifier (UML); Pattern recognition (psychology); Convolutional neural network; Discriminative model; Feature extraction; Contextual image classification; Weighting; Feature (linguistics); Machine learning; Image (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":[],"consensus_categories":[],"category_scores_codex":[0.00007206021,0.00007243139,0.00006820912,0.00002072493,0.0006660469,0.0002191053,0.0007621628,0.00001849318,0.00003681991],"category_scores_gemma":[0.00002482967,0.00006579989,0.0000388526,0.00003313138,0.00004488945,0.0006599962,0.0002192568,0.00005723942,0.00008257059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001274196,"about_ca_system_score_gemma":0.000007752269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002103245,"about_ca_topic_score_gemma":0.00006345932,"domain_scores_codex":[0.9993874,0.000009334575,0.00009464206,0.0002569058,0.00007864898,0.0001730563],"domain_scores_gemma":[0.999049,0.00007850901,0.00009215386,0.0006753085,0.0000592047,0.00004581029],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001178573,0.00005977732,0.0001172454,0.00001143515,0.00001555978,0.000003283167,0.0000844763,0.00002244534,0.007270332,0.09257658,0.1384409,0.7613862],"study_design_scores_gemma":[0.001963782,0.0002528241,0.02394621,0.00002742885,0.00002151026,0.0000514818,0.00006060458,0.0278439,0.06117463,0.5867338,0.2971446,0.0007792052],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001312785,0.00001569939,0.9774399,0.01001218,0.0001490717,0.0004215783,0.00001739402,0.0001699049,0.01046144],"genre_scores_gemma":[0.128441,0.00001862939,0.8667873,0.001538242,0.0002317423,0.0001860238,0.00005808102,0.00001222663,0.002726764],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.760607,"threshold_uncertainty_score":0.5122762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05639775682315842,"score_gpt":0.3358514724513144,"score_spread":0.2794537156281559,"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."}}