论文标题
增强循环一致性正规化，用于未配对的图像到图像翻译
Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation
论文作者
论文摘要
由于最新的生成对抗网络（GAN）的进步，未配对的图像到图像（I2I）翻译在模式识别和计算机视觉上受到了极大的关注。但是，由于缺乏明确的监督，未配对的i2i模型通常无法生成逼真的图像，尤其是在具有不同背景和姿势的挑战性数据集中。因此，对于I2i翻译的gan和应用是必不可少的。本文中，我们提出了增强的环状一致性正则化（ACCR），这是一种用于未配对I2i翻译的新型正则化方法。我们的主要思想是实施一致性正规化，源自对歧视者的半监督学习，利用真实，假，重建和增强样本。当喂食的原始图像和扰动图像对时，我们将鉴别器正规化以输出类似的预测。我们从定性地阐明了为什么对假和重建样品的一致性正规化效果很好。从数量上讲，我们的方法在现实世界翻译中优于一致性正则化GAN（CR-GAN），并证明了针对多种数据增强变体和周期一致性约束的功效。
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.
