Pith. sign in

REVIEW

Multimodal Image-to-Image Translation via Mutual Information Estimation and Maximization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2008.03529 v7 pith:CIWRHTR5 submitted 2020-08-08 cs.CV cs.LGeess.IVstat.ML

Multimodal Image-to-Image Translation via Mutual Information Estimation and Maximization

classification cs.CV cs.LGeess.IVstat.ML
keywords codeinformationlatentcgansconditionaldomainimagemutual
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Multimodal image-to-image translation (I2IT) aims to learn a conditional distribution that explores multiple possible images in the target domain given an input image in the source domain. Conditional generative adversarial networks (cGANs) are often adopted for modeling such a conditional distribution. However, cGANs are prone to ignore the latent code and learn a unimodal distribution in conditional image synthesis, which is also known as the mode collapse issue of GANs. To solve the problem, we propose a simple yet effective method that explicitly estimates and maximizes the mutual information between the latent code and the output image in cGANs by using a deep mutual information neural estimator in this paper. Maximizing the mutual information strengthens the statistical dependency between the latent code and the output image, which prevents the generator from ignoring the latent code and encourages cGANs to fully utilize the latent code for synthesizing diverse results. Our method not only provides a new perspective from information theory to improve diversity for I2IT but also achieves disentanglement between the source domain content and the target domain style for free.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.