Unpaired image-to-image (I2I) translation has received considerable attention
in pattern recognition and computer vision because of recent advancements in
generative adversarial networks (GANs). However, due to the lack of explicit
supervision, unpaired I2I models often fail to generate realistic images,
especially in challenging datasets with different backgrounds and poses. Hence,
stabilization is indispensable for GANs and applications of I2I translation.
Herein, we propose Augmented Cyclic Consistency Regularization (ACCR), a novel
regularization method for unpaired I2I translation. Our main idea is to enforce
consistency regularization originating from semi-supervised learning on the
discriminators leveraging real, fake, reconstructed, and augmented samples. We
regularize the discriminators to output similar predictions when fed pairs of
original and perturbed images. We qualitatively clarify why consistency
regularization on fake and reconstructed samples works well. Quantitatively,
our method outperforms the consistency regularized GAN (CR-GAN) in real-world
translations and demonstrates efficacy against several data augmentation
variants and cycle-consistent constraints.

本文提出了一种新的正则化方法 —— 增强循环一致性正则化（ACCR），该方法适用于无配对图像转换。通过使用真实、假的、重构的和增强的样本，我们试图在辨别器上施加来自半监督学习的一致性正则化。实验结果表明，该方法在诸多方面表现优异，尤其在真实世界的转换中表现得更为有效。