{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005818576,0.0004801285,0.0004724374,0.0004236165,0.0002066487,0.0006194846,0.0008754869,0.0006027472,0.00284253],"category_scores_gemma":[0.002457886,0.0002709414,0.0005020409,0.0004723661,0.0007361436,0.001131268,0.001180252,0.001132064,0.0007734232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006343249,"about_ca_system_score_gemma":0.0004633916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001451393,"about_ca_topic_score_gemma":0.001955268,"domain_scores_codex":[0.999698,0.00008014831,0.00001322801,0.00005929988,0.0001208974,0.00002845353],"domain_scores_gemma":[0.9995235,0.0001803645,0.00005652038,0.0001307893,0.00007509874,0.00003379559],"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":[0.0003139824,0.0001173201,0.001685714,0.0001718113,0.00006096328,0.0001918147,0.0001690881,0.5208165,0.05523647,0.131985,0.004026617,0.2852248],"study_design_scores_gemma":[0.000006801386,0.00002177737,0.00007420326,0.00000270315,0.000003033786,0.00003246552,0.000003764455,0.9861136,0.004867226,0.008003528,0.0008670043,0.000003939085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00637531,0.00006140152,0.9924217,0.00006461604,0.00001522026,0.00001491584,0.00001946642,0.0003373588,0.0006899942],"genre_scores_gemma":[0.5209213,0.0002530058,0.4729968,0.0002415103,0.0000731503,0.0001303985,0.0002002135,0.0003125003,0.004871048],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00284253,"threshold_uncertainty_score":0.009509146,"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."}}