{"id":"W2950339535","doi":"10.48550/arxiv.1806.03968","title":"CapsGAN: Using Dynamic Routing for Generative Adversarial Networks","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; MNIST database; Normalization (sociology); Artificial intelligence; Knot (papermaking); Image translation; Algorithm; Clipping (morphology); Computer vision; Image (mathematics); Deep learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007912665,0.0009239722,0.0005103681,0.0004118813,0.0002646983,0.0006694819,0.001029013,0.0009243463,0.003660991],"category_scores_gemma":[0.002165136,0.0004368018,0.0005187785,0.0002792397,0.0009451205,0.001063341,0.001475646,0.001763774,0.001007117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007437007,"about_ca_system_score_gemma":0.000457866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001490483,"about_ca_topic_score_gemma":0.00228872,"domain_scores_codex":[0.9997069,0.0001184304,0.000007650043,0.00007261115,0.00006589861,0.00002850528],"domain_scores_gemma":[0.9994572,0.0003382772,0.00004237314,0.00009216601,0.00004091594,0.00002910789],"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":[0.00008450291,0.00003155253,0.0003373074,0.0000532304,0.00004795095,0.00009812536,0.00005094023,0.8744097,0.00499835,0.0518188,0.004789377,0.06328018],"study_design_scores_gemma":[0.000005120517,0.00001374206,0.0000292689,0.000004888875,0.00000366075,0.00002351773,0.00000329615,0.9833571,0.001150192,0.01377713,0.001627676,0.000004385704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004564151,0.0001551056,0.9912171,0.0002317401,0.00005460734,0.00003083512,0.00006173105,0.0009343699,0.002750404],"genre_scores_gemma":[0.5964943,0.0005217897,0.386922,0.0008099516,0.0001570074,0.0002790743,0.0006241119,0.0007841139,0.0134077],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003660991,"threshold_uncertainty_score":0.0122472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07079669769047088,"score_gpt":0.2088384478779232,"score_spread":0.1380417501874524,"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."}}