{"id":"W2962714319","doi":"10.1109/iccv.2015.483","title":"Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions","year":2015,"lang":"en","type":"preprint","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":339,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Samsung; Natural Sciences and Engineering Research Council of Canada; California Institute of Technology","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Embedding; Deep learning; Natural language processing; Machine learning; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008693612,0.001405146,0.0006863205,0.001374107,0.0002963352,0.0007868441,0.001394373,0.001296702,0.00107613],"category_scores_gemma":[0.003771846,0.0004025224,0.0005974079,0.0008241546,0.0005273143,0.002015386,0.0005628263,0.001150501,0.0006206772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001622724,"about_ca_system_score_gemma":0.0006268678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01485206,"about_ca_topic_score_gemma":0.02155739,"domain_scores_codex":[0.9995926,0.00008410085,0.00002175747,0.0001591915,0.00006628461,0.00007602236],"domain_scores_gemma":[0.9983134,0.0008949894,0.0001662543,0.000146619,0.0003678466,0.0001108505],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000733214,0.0007761518,0.02996995,0.0003965604,0.000193088,0.0004911846,0.0001415084,0.6144298,0.01087527,0.004144277,0.02013901,0.3177099],"study_design_scores_gemma":[0.000005976523,0.00002487657,0.0009508304,0.000009642692,0.000007648903,0.00001727187,0.00001237995,0.9957656,0.00163724,0.001387161,0.0001765237,0.000004803802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7873402,0.002877753,0.1965977,0.0008341493,0.0003087013,0.0001374102,0.00364215,0.004274057,0.003987936],"genre_scores_gemma":[0.9671494,0.0003079262,0.02362514,0.0001392198,0.00005541226,0.00004937812,0.005403719,0.00005346196,0.00321637],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01485206,"threshold_uncertainty_score":0.02953118,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1063302938170178,"score_gpt":0.2994168398208519,"score_spread":0.1930865460038341,"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."}}