no code implementations • 23 Jan 2019 • Yeu-Chern Harn, Zhenghao Chen, Vladimir Jojic
In this work, we propose a composition/decomposition framework for adversarially training generative models on composed data - data where each sample can be thought of as being constructed from a fixed number of components.
no code implementations • ICLR 2018 • Yeu-Chern Harn, Vladimir Jojic
We present 3C-GAN: a novel multiple generators structures, that contains one conditional generator that generates a semantic part of an image conditional on its input label, and one context generator generates the rest of an image.
no code implementations • 30 Mar 2016 • Tianxiang Gao, Vladimir Jojic
The degrees of freedom in deep networks are dramatically smaller than the number of parameters, in some real datasets several orders of magnitude.
no code implementations • CVPR 2014 • Enliang Zheng, Enrique Dunn, Vladimir Jojic, Jan-Michael Frahm
We propose a multi-view depthmap estimation approach aimed at adaptively ascertaining the pixel level data associations between a reference image and all the elements of a source image set.