{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001272396,0.0009263787,0.0007585649,0.0005135089,0.0003079767,0.0006236206,0.00116269,0.00106473,0.002342666],"category_scores_gemma":[0.003425838,0.0003688941,0.0007110562,0.0006549497,0.001278887,0.001649284,0.001670101,0.002501568,0.0006705419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00075598,"about_ca_system_score_gemma":0.0007286956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002292319,"about_ca_topic_score_gemma":0.002561,"domain_scores_codex":[0.9993883,0.0002595924,0.00002287137,0.0001637519,0.0001162771,0.0000492005],"domain_scores_gemma":[0.9989007,0.0006820757,0.00009152868,0.0002105127,0.00007295125,0.0000421937],"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":[0.0002025398,0.0001148199,0.000655242,0.0001341672,0.00007753246,0.0001448475,0.0001425071,0.7820745,0.00885786,0.04509314,0.004465953,0.1580369],"study_design_scores_gemma":[0.000007194037,0.0000171341,0.00005175194,0.000005942543,0.0000046183,0.00002146731,0.000005510764,0.981968,0.002137069,0.01517987,0.0005970944,0.000004406892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01707619,0.0004729215,0.9786299,0.0004036913,0.00004776179,0.00003582221,0.0001174351,0.001015809,0.002200479],"genre_scores_gemma":[0.7683337,0.0005576673,0.2230262,0.0005011028,0.000106383,0.0001668425,0.000655674,0.0002885311,0.00636398],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002342666,"threshold_uncertainty_score":0.007836998,"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."}}