Abstract: We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss ...
Abstract: Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results