Artificial Intelligence


Casl-Gan: Multi-Domain Image-to-Image Translation Gan

Authors: JeongIk Cho

StarGAN, which has impressive performance in multi-domain image-to-image translation. Reconstruction loss of StarGAN requires reconstructed data from generated data, which means to get reconstruction loss, need to use the generator once more. Simplified content loss uses already generated data, reduces the amount of computation and memory usage. Also, propose image framing to prevent background distortion.

Comments: 18 Pages.

Download: PDF

Submission history

[v1] 2019-09-03 20:56:00
[v2] 2019-10-05 10:38:22
[v3] 2019-11-05 18:35:57
[v4] 2019-11-19 21:46:23
[v5] 2019-12-01 08:06:42
[v6] 2019-12-21 10:31:55

Unique-IP document downloads: 16 times is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. will not be responsible for any consequences of actions that result from any form of use of any documents on this website.

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus