{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008087962,0.0003861582,0.000362051,0.0002391618,0.000433546,0.0007737928,0.001244259,0.000362715,0.00008441643],"category_scores_gemma":[0.0001621543,0.0003973483,0.0001915482,0.0003544796,0.0001333943,0.0005667206,0.002009909,0.001272865,0.00003690282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003078192,"about_ca_system_score_gemma":0.0004382502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000167757,"about_ca_topic_score_gemma":0.00003877737,"domain_scores_codex":[0.9969845,0.0002687932,0.0006034828,0.0008707875,0.0006647605,0.0006077026],"domain_scores_gemma":[0.9979564,0.0001539218,0.0003552343,0.0007224339,0.0004509249,0.0003610793],"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":[0.000006249074,0.00003951323,0.001800639,0.00001200535,0.00004488005,0.00001335328,0.0005359397,0.9660966,0.00003321415,0.02622185,0.001012396,0.004183308],"study_design_scores_gemma":[0.0003136552,0.0000270526,0.0009244781,0.00004839468,0.00002459168,0.00005849905,0.0002227701,0.994287,0.000002146264,0.002788305,0.0008924758,0.0004106521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008589071,0.0004513855,0.9740276,0.0002238757,0.002516706,0.0003015152,0.000006248842,0.0006743855,0.01320917],"genre_scores_gemma":[0.8483964,0.000008584776,0.149372,0.0008663578,0.000544923,0.0000240857,0.00008282716,0.00003100421,0.0006737983],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8398073,"threshold_uncertainty_score":0.9998478,"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."}}