公开(公告)号：US11869170B2

公开(公告)日：2024-01-09

申请号：US17293754

申请日：2019-11-18

Applicant: Google LLC

Inventor： David Berthelot ,  Ian Goodfellow

IPC: G06T3/40 ,  G06N3/08 ,  G06T5/50 ,  G06F18/22 ,  G06N3/045

CPC classification number: G06T3/4046 ,  G06F18/22 ,  G06N3/045 ,  G06N3/08 ,  G06T3/4053 ,  G06T5/50

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes receiving a training image and a ground truth super-resolution image; processing a first training network input comprising the training image using the neural network to generate a first training super-resolution image; processing a first critic input generated from (i) the training image and (ii) the ground truth super-resolution image using a critic neural network to map the first critic input to a latent representation; processing a second critic input generated from (i) the training image and (ii) the first training super-resolution image using the critic neural network to map the second critic input to a latent representation; determining a gradient of a generator loss function that measures a distance between the latent representations of the critic inputs; and determining an update to the parameters.