Log In Sign Up

Evaluation of Correctness in Unsupervised Many-to-Many Image Translation

by   Dina Bashkirova, et al.

Given an input image from a source domain and a "guidance" image from a target domain, unsupervised many-to-many image-to-image (UMMI2I) translation methods seek to generate a plausible example from the target domain that preserves domain-invariant information of the input source image and inherits the domain-specific information from the guidance image. For example, when translating female faces to male faces, the generated male face should have the same expression, pose and hair color as the input female image, and the same facial hairstyle and other male-specific attributes as the guidance male image. Current state-of-the art UMMI2I methods generate visually pleasing images, but, since for most pairs of real datasets we do not know which attributes are domain-specific and which are domain-invariant, the semantic correctness of existing approaches has not been quantitatively evaluated yet. In this paper, we propose a set of benchmarks and metrics for the evaluation of semantic correctness of UMMI2I methods. We provide an extensive study how well the existing state-of-the-art UMMI2I translation methods preserve domain-invariant and manipulate domain-specific attributes, and discuss the trade-offs shared by all methods, as well as how different architectural choices affect various aspects of semantic correctness.


page 7

page 8

page 13

page 14

page 15

page 16

page 18

page 19


Disentangled Unsupervised Image Translation via Restricted Information Flow

Unsupervised image-to-image translation methods aim to map images from o...

Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound

Unsupervised image-to-image translation is a class of computer vision pr...

ZstGAN: An Adversarial Approach for Unsupervised Zero-Shot Image-to-Image Translation

Image-to-image translation models have shown remarkable ability on trans...

Learning Unsupervised Cross-domain Image-to-Image Translation Using a Shared Discriminator

Unsupervised image-to-image translation is used to transform images from...

Cross-Domain Image Manipulation by Demonstration

In this work we propose a model that can manipulate individual visual at...

Manipulating Medical Image Translation with Manifold Disentanglement

Medical image translation (e.g. CT to MR) is a challenging task as it re...

Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplar

Conventional face super-resolution methods usually assume testing low-re...