Kernel Inception Distance: 7.47
Papers with Code · CC BY-SA 4.0
Image-to-Image Translation
Image-to-Image Translation is a task in computer vision and machine learning where the goal is to learn a mapping between an input image and an output image, such that the output image can be used to perform a specific task, such as style transfer, data augmentation, or image restoration.
<span style="color:grey; opacity: 0.6">( Image credit: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks )</span>
논문
DFID: 26.1FID: 26.9
Frechet Inception Distance: 110.5Number of params: 28.2M
Frechet Inception Distance: 112.3Number of params: 15.9M
mAP: 38.8
mAP: 42.5
FID: 14.4
mIoU: 63.3Per-pixel Accuracy: 92.1%fwIOU: 85.7
Classification Error: 4.10%
mAP: 34.6
mAP: 27.6
FID: 50.43
mIoU: 59.6
Kernel Inception Distance: 10.23
Classification Error: 8.07%
Kernel Inception Distance: 4.4
mAP: 47.6
mAP: 36.9
FID: 48.15
Classification Error: 2.12%