Evaluation study of unsupervised face-to-face translation using generative adversarial networks

Muhamad Iqbal, M. Rahmat Widyanto, Risman Adnan, T. Basaruddin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Cross-domain image-to-image translation provides mechanism to capture special characteristics of one image collection and convert into other image collection with different representations. Recent research on generative learning have produced powerful image-toimage translation methods in supervised setting, where paired training datasets are available. However, collecting paired training data is difficult, expensive and required manual authoring. We present an evaluation study of recent unsupervised Generative Adversarial Network (GAN) models that can learn to translate a facial image from a source domain X to a target domain Y without paired labeled training dataset. Each GAN model is trained on the same facial image dataset and comparable hyperparameters. We report a comparison result using same GAN model evaluation metrics.

Original languageEnglish
Title of host publicationICMLSC 2019 - Proceedings of the 3rd International Conference on Machine Learning and Soft Computing
PublisherAssociation for Computing Machinery
Number of pages6
ISBN (Electronic)9781450366120
Publication statusPublished - 25 Jan 2019
Event3rd International Conference on Machine Learning and Soft Computing, ICMLSC 2019 - Da Lat, Viet Nam
Duration: 25 Jan 201928 Jan 2019

Publication series

NameACM International Conference Proceeding Series


Conference3rd International Conference on Machine Learning and Soft Computing, ICMLSC 2019
Country/TerritoryViet Nam
CityDa Lat


  • Facial image
  • Generative adversarial network
  • Image-to-image translation
  • Model evaluation

Cite this