AbstractSince its first proposal in 2018, deep image prior has emerged as a very powerful unsupervised deep learning technique for solving inverse problems. The approach has demonstrated very encouraging empirical success in image denoising, deblurring, super-resolution etc. However, there are also several known drawbacks of the approach, notably high computational expense. In this talk, we des...
课程描述 DescriptionContent: Research results of the Instructor.Topics include : MLE's Bias Pathology, model updated MLE and Wallace's MM method. Artificially augmented samples, shrinkage and MSE reduction.Elegant Nonparametric Estimation of a density and Matching Estimation with convergence rates via Minimum Distance Methods. Tukey's Poly-efficiency. More topics if time permits.预备知识 Prereq...