{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000740185,0.002249331,0.001599592,0.001393702,0.00040378,0.001376485,0.003164491,0.001473358,0.004732623],"category_scores_gemma":[0.001482785,0.0007246883,0.0009762406,0.001161134,0.0007497804,0.004044634,0.002327733,0.002039564,0.002271106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009216302,"about_ca_system_score_gemma":0.0009809877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0030493,"about_ca_topic_score_gemma":0.004116293,"domain_scores_codex":[0.9995198,0.00005592698,0.00002058322,0.0001960216,0.0001204476,0.00008718979],"domain_scores_gemma":[0.9996834,0.00006531083,0.00003934871,0.0000894076,0.00007988623,0.00004279608],"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":[0.0006221466,0.0004486708,0.00221143,0.0002848069,0.0002742544,0.0002703707,0.00008103568,0.1406328,0.02235403,0.02055012,0.02759485,0.7846755],"study_design_scores_gemma":[0.00003418855,0.0001020202,0.0003041426,0.00001875263,0.00003992607,0.00009747039,0.00001627349,0.9677942,0.009057694,0.01641304,0.00610397,0.00001845264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01947867,0.001076122,0.9677759,0.0003376664,0.0002902304,0.0001025505,0.0007058706,0.00648323,0.003749721],"genre_scores_gemma":[0.4065723,0.0008761149,0.5726723,0.0008542354,0.0002929028,0.0003783972,0.005223781,0.000647969,0.01248195],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004732623,"threshold_uncertainty_score":0.01583213,"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."}}