Transcription of Reusing Discriminators for Encoding: Towards Unsupervised ...
{{id}} {{{paragraph}}}
Example: bankruptcy
Reusing Discriminators for Encoding: Towards Unsupervised ...
Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image translation Runfa Chen, Wenbing Huang, Binghui Huang, Fuchun Sun , Bin Fang Institute for Artificial Intelligence, Tsinghua University (THUAI). Beijing National Research Center for Information Science and Technology (BNRist), State Key Lab on Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, fcsun@, Abstract Unsupervised image-to-image translation is a central task in computer vision. Current translation frameworks will abandon the discriminator once the training process is completed. This paper contends a novel role of the dis- criminator by Reusing it for encoding the images of the tar- get domain. The proposed architecture, termed as NICE- GAN, exhibits two advantageous patterns over previous ap- proaches: First, it is more compact since no independent encoding component is required; Second, this plug-in en- coder is directly trained by the adversary loss, making it more informative and trained more effectively if a multi- Figure 1: Illustrative difference between CycleGAN-alike scale discriminator is applied.
Unsupervised image-to-image translation. In terms of unsupervised image-to-image translation with unpaired training data, CycleGAN [40], DiscoGAN [17], Dual-GAN [38] preserve key attributes between the input and the translated image by using a cycle-consistency loss. Vari-ous studies have been proposed towards extension of Cy-cleGAN.
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: