{"id":"W3207093560","doi":"10.1109/tip.2021.3125266","title":"A Domain Gap Aware Generative Adversarial Network for Multi-Domain Image Translation","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Image Processing","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Department of Agriculture","keywords":"Consistency (knowledge bases); Computer science; Constraint (computer-aided design); Local consistency; Regularization (linguistics); Artificial intelligence; Image translation; Generative grammar; Generator (circuit theory); Image (mathematics); Domain (mathematical analysis); Translation (biology); Theoretical computer science; Pattern recognition (psychology); Mathematics; Constraint satisfaction; Probabilistic logic","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":[0.0004725017,0.0005966601,0.0004881185,0.0001716989,0.0006316541,0.0004253771,0.0003483849,0.0008890349,0.00007019138],"category_scores_gemma":[0.00001552809,0.0006922589,0.0005883156,0.0002794747,0.0001767168,0.00003052948,0.00002071172,0.001028823,0.000005259047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001961686,"about_ca_system_score_gemma":0.001272409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000382431,"about_ca_topic_score_gemma":0.0002744516,"domain_scores_codex":[0.9966291,0.000295749,0.0005515021,0.001373565,0.0004291809,0.0007208937],"domain_scores_gemma":[0.9983631,0.00003044851,0.0002443357,0.0005563494,0.0006174449,0.0001882917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008428065,0.0002786824,1.305664e-7,0.0005782131,0.0003396811,0.00002929063,0.0006268467,0.03959913,0.9243658,0.000002851404,0.0003289514,0.03300767],"study_design_scores_gemma":[0.004000346,0.0003346346,0.00000135377,0.0005981687,0.000261324,0.00003603932,0.0007132135,0.06368773,0.9264094,0.0004718377,0.002430312,0.001055625],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002516413,0.00167412,0.9920266,0.0002981568,0.001074921,0.001710033,0.0004937694,0.00007402772,0.0001319165],"genre_scores_gemma":[0.1625778,0.0004668174,0.8315462,0.0003131269,0.001307097,0.001636996,0.001445478,0.0002872379,0.0004191889],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1604804,"threshold_uncertainty_score":0.9995528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03824900001564071,"score_gpt":0.3318494300514757,"score_spread":0.293600430035835,"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."}}