DFID: 35.6FID: 34.4LPIPS: 0.505
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
classification score: 78.1
Classification Accuracy: 76.0%
Accuracy: 74.8
FID: 42.4
Classification Accuracy: 90.4%
Accuracy: 52.4
Accuracy: 79.8
LPIPS: 0.400
Accuracy: 57.4
mIoU: 40.4FID: 45.8
mIoU: 17.4Accuracy: 71.6%FID: 97.8
PSNR: 21.65
Accuracy: 71.9
mIoU: 75.9
mIoU: 16.5Accuracy: 68.6%FID: 99.0
mIoU: 30.8Accuracy: 82.9%FID: 63.3
mIoU: 13.1Accuracy: 74.7%FID: 67.7
FID: 35.5
mIoU: 77.7
PSNR: 18.57
Classification Accuracy: 84.4%
Classification Accuracy: 73.6%
PSNR: 9.42
Accuracy: 73.3
mIoU: 40.4FID: 48.6