Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationImage-to-Image TranslationTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Content-Preserving Unpaired Translation from Simulated to Realistic Ultrasound Images
Interactive simulation of ultrasound imaging greatly facilitates sonography training. Although ray-tracing based methods have shown promising results, obtaining realistic images requires substantial modeling effort and m…
DisentanglementTranslationEfficient Unpaired Image Dehazing with Cyclic Perceptual-Depth Supervision
Image dehazing without paired haze-free images is of immense importance, as acquiring paired images often entails significant cost. However, we observe that previous unpaired image dehazing approaches tend to suffer from…
Image DehazingOne-to-one Mapping for Unpaired Image-to-image Translation
Recently image-to-image translation has attracted significant interests in the literature, starting from the successful use of the generative adversarial network (GAN), to the introduction of cyclic constraint, to extens…
Generative Adversarial NetworkImage GenerationImage-to-Image TranslationTranslationA Strictly Bounded Deep Network for Unpaired Cyclic Translation of Medical Images
Medical image translation is an ill-posed problem. Unlike existing paired unbounded unidirectional translation networks, in this paper, we consider unpaired medical images and provide a strictly bounded network that yiel…
Dictionary LearningGenerative Adversarial NetworkTranslationGenerative Landmarks
We propose a general purpose approach to detect landmarks with improved temporal consistency, and personalization. Most sparse landmark detection methods rely on laborious, manually labelled landmarks, where inconsistenc…
Generative Adversarial NetworkTranslation