10 years of news and resources for members of the IEEE Signal Processing Society
Researchers from University of California, Berkeley have developed an AI that turns a horse video into a zebra video.
The following is from the abstract of the authors' paper, titled "Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks".
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 pairs. However, for many tasks, paired training data will not be available. We present an approach for learning to translate an image from a source domain X to a target domain Y in the absence of paired examples. Our goal is to learn a mapping G: X → Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss. Because this mapping is highly under-constrained, we couple it with an inverse mapping F: Y → X and introduce a cycle consistency loss to push F(G(X)) ≈ X (and vice versa). Qualitative results are presented on several tasks where paired training data does not exist, including collection style transfer, object transfiguration, season transfer, photo enhancement, etc. Quantitative comparisons against several prior methods demonstrate the superiority of our approach.
For more details, please visit https://junyanz.github.io/CycleGAN/.
AI Learns to Synthesize Pictures of Animals
Courtesy of Two Minute Papers
|Call for Nominations: Division IX Director-Elect||5 February 2018|
|Call for Officer Nominations: Vice President-Technical Directions||12 February 2018|
|Call for Nominations for Editor-in-Chief||23 March 2018|
© Copyright 2018 IEEE – All rights reserved. Use of this website signifies your agreement to the IEEE Terms and Conditions.
A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.