{"id":"W2912083667","doi":"10.48550/arxiv.1901.07124","title":"Linearized Multi-Sampling for Differentiable Image Transformation","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Bilinear interpolation; Differentiable function; Upsampling; Computer science; Image scaling; Pixel; Artificial neural network; Artificial intelligence; Image (mathematics); Hessian matrix; Interpolation (computer graphics); Sampling (signal processing); Deep neural networks; Transformation (genetics); Algorithm; Mathematics; Image processing; Computer vision; Applied mathematics; Filter (signal processing); Mathematical analysis","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001129428,0.0002682705,0.0002999495,0.0001501758,0.0001991542,0.0001326788,0.001366599,0.0002056574,0.000008009763],"category_scores_gemma":[0.00001779114,0.0003115473,0.000231747,0.0003507588,0.00004476431,0.0006132137,0.000611314,0.0003821388,0.00008009184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001260886,"about_ca_system_score_gemma":0.00007946489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001325494,"about_ca_topic_score_gemma":0.00000786871,"domain_scores_codex":[0.9984469,0.00004104398,0.000226906,0.0008761958,0.00006118738,0.0003478134],"domain_scores_gemma":[0.9982314,0.0001887222,0.0002364587,0.001061933,0.0001807552,0.0001007274],"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":[0.00003661741,0.0001160785,0.00008600191,0.000188544,0.00005389514,0.000003265321,0.0001969931,0.8912278,0.001230554,0.1056883,0.0001111731,0.001060807],"study_design_scores_gemma":[0.0009083798,0.00002070611,0.0001268237,0.00004325184,0.00004166534,8.081637e-7,0.00001459075,0.970402,0.0007639687,0.02593505,0.001414401,0.0003283756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01846792,0.00002113268,0.9791615,0.000125694,0.0003243535,0.001253374,0.00004151215,0.0003434188,0.0002610685],"genre_scores_gemma":[0.8397553,0.0001001884,0.1584814,0.00006239781,0.00006071773,0.00001293007,0.0001064764,0.00002364735,0.001396962],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8212873,"threshold_uncertainty_score":0.9999337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1269013367588581,"score_gpt":0.2375379686668606,"score_spread":0.1106366319080024,"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."}}