From 91b1fd156c7c9a7216ae74de43f022e38c03df8e Mon Sep 17 00:00:00 2001 From: Aladdin Persson Date: Sat, 6 Mar 2021 21:09:41 +0100 Subject: [PATCH] cyclegan --- ML/Pytorch/GANs/CycleGAN/README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/ML/Pytorch/GANs/CycleGAN/README.md b/ML/Pytorch/GANs/CycleGAN/README.md index 30529c6..1e8e1a1 100644 --- a/ML/Pytorch/GANs/CycleGAN/README.md +++ b/ML/Pytorch/GANs/CycleGAN/README.md @@ -25,7 +25,8 @@ Edit the config.py file to match the setup you want to use. Then run train.py ### Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks by Jun-Yan Zhu, Taesung Park, Phillip Isola, Alexei A. Efros #### Abstract -Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, for many tasks, paired training data will not be available. We present an approach for learning to translate an image from a source domain X to a target domain Y in the absence of paired examples. Our goal is to learn a mapping G:X→Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss. Because this mapping is highly under-constrained, we couple it with an inverse mapping F:Y→X and introduce a cycle consistency loss to push F(G(X))≈X (and vice versa). Qualitative results are presented on several tasks where paired training data does not exist, including collection style transfer, object transfiguration, season transfer, photo enhancement, etc. Quantitative comparisons against several prior methods demonstrate the superiority of our approach. ``` +Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, for many tasks, paired training data will not be available. We present an approach for learning to translate an image from a source domain X to a target domain Y in the absence of paired examples. Our goal is to learn a mapping G:X→Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss. Because this mapping is highly under-constrained, we couple it with an inverse mapping F:Y→X and introduce a cycle consistency loss to push F(G(X))≈X (and vice versa). Qualitative results are presented on several tasks where paired training data does not exist, including collection style transfer, object transfiguration, season transfer, photo enhancement, etc. Quantitative comparisons against several prior methods demonstrate the superiority of our approach. +``` @misc{zhu2020unpaired, title={Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks}, author={Jun-Yan Zhu and Taesung Park and Phillip Isola and Alexei A. Efros},