A hybrid approach between adversarial generative networks and actor-critic policy gradient for low rate high-resolution image compression

Title: A hybrid approach between adversarial generative networks and actor-critic policy gradient for low rate high-resolution image compression
Authors: Savioli, N
Item Type: Conference Paper
Abstract: Image compression is an essential approach for decreasing the size in bytes of the image without deteriorating the quality of it. Typically, classic algorithms are used but recently deep-learning has been successfully applied. In this work, is presented a deep super-resolution work-flow for image compression that maps low-resolution JPEG image to the high-resolution. The pipeline consists of two components: first, an encoder-decoder neural network learns how to transform the downsampling JPEG images to high resolution. Second, a combination between Generative Adversarial Networks (GANs) and reinforcement learning Actor-Critic (A3C) loss pushes the encoder-decoder to indirectly maximize High Peak Signal-to-Noise Ratio (PSNR). Although PSNR is a fully differentiable metric, this work opens the doors to new solutions for maximizing non-differential metrics through an end-to-end approach between encoder-decoder networks and reinforcement learning policy gradient methods.
Date of Acceptance: 13-Jun-2019
URI: http://hdl.handle.net/10044/1/72797
Publisher: IEEE
Conference Name: IEEE Conference on Computer Vision and Pattern Recognition, Workshop and Challenge on Learned Image Compression (CLIC) 2019
Keywords: eess.IV
eess.IV
cs.LG
stat.ML
eess.IV
eess.IV
cs.LG
stat.ML
Notes: 4 pages, 2 figures, IEEE Conference on Computer Vision and Pattern Recognition, Workshop and Challenge on Learned Image Compression (CLIC) 2019
Publication Status: Accepted
Start Date: 2019-06-17
Finish Date: 2019-06-17
Conference Place: Long Beach, CA, USA
Appears in Collections:Clinical Sciences
Imaging Sciences



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons