Unsupervised Cross-Domain Image Generation

7 Nov 2016Yaniv TaigmanAdam PolyakLior Wolf

We study the problem of transferring a sample in one domain to an analog sample in another domain. Given two related domains, S and T, we would like to learn a generative function G that maps an input sample from S to the domain T, such that the output of a given function f, which accepts inputs in either domains, would remain unchanged... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Unsupervised Image-To-Image Translation SVNH-to-MNIST DTN Classification Accuracy 84.4% # 2