3 papers
cs.CV2020
The Surprising Effectiveness of Linear Unsupervised Image-to-Image Translation
Eitan Richardson, Yair Weiss
Unsupervised image-to-image translation is an inherently ill-posed problem. Recent methods based on deep encoder-decoder architectures have shown impressive results, but we show th…
cs.LG2020
A Bayes-Optimal View on Adversarial Examples
Eitan Richardson, Yair Weiss
Since the discovery of adversarial examples - the ability to fool modern CNN classifiers with tiny perturbations of the input, there has been much discussion whether they are a "bu…
cs.CV2018
On GANs and GMMs
Eitan Richardson, Yair Weiss
A longstanding problem in machine learning is to find unsupervised methods that can learn the statistical structure of high dimensional signals. In recent years, GANs have gained m…