{"id":"W3159735872","doi":"10.48550/arxiv.2104.15082","title":"Semantic Relation Preserving Knowledge Distillation for Image-to-Image Translation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"March of Dimes Canada","funders":"","keywords":"Computer science; Image (mathematics); Relation (database); Task (project management); Inference; Image translation; Translation (biology); Artificial intelligence; Feature (linguistics); Distillation; Generative grammar; Machine learning; Semantic feature; Matrix (chemical analysis); Natural language processing; Pattern recognition (psychology); Data mining","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003597157,0.0003085879,0.0003383541,0.0002344983,0.0002860741,0.0004107502,0.0008282585,0.0002364425,0.00002807993],"category_scores_gemma":[0.0001395722,0.0003749452,0.0002791397,0.0006575009,0.00004302778,0.001125068,0.0007492289,0.000264566,0.00003245669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001731117,"about_ca_system_score_gemma":0.000164539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006395564,"about_ca_topic_score_gemma":0.0001481563,"domain_scores_codex":[0.9978936,0.0002477395,0.0002731094,0.001168705,0.00008895983,0.0003278598],"domain_scores_gemma":[0.9979633,0.0002817806,0.0002166977,0.0008846745,0.0005083784,0.0001451544],"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":[0.00005149373,0.0001246063,0.0003172176,0.0003005089,0.0001438115,0.00004181493,0.001791017,0.9745737,0.005545491,0.007680599,0.0006672769,0.008762443],"study_design_scores_gemma":[0.0003517393,0.00003503847,0.002342654,0.0001592448,0.0001018628,0.000001074208,0.00006574929,0.9897482,0.001458447,0.004747997,0.0005824509,0.0004054836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02398358,0.0000983015,0.9716123,0.0003009509,0.0007417852,0.0007923263,0.00001718907,0.0001570991,0.002296445],"genre_scores_gemma":[0.9099974,0.00004956557,0.08896147,0.00002497362,0.0002117492,0.000005263784,0.00009295611,0.00002503213,0.0006315882],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8860138,"threshold_uncertainty_score":0.9998702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07756189650363152,"score_gpt":0.2157390321012007,"score_spread":0.1381771355975692,"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."}}