paper-with-me

Papers

Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation

2020-02-29 · Takehiko Ohkawa, Naoto Inoue, Hirokatsu Kataoka, Nakamasa Inoue

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.

📄 PDF Abstract BibTeX arXiv:2003.00187

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationImage-to-Image TranslationTranslation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dogecoin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Content-Preserving Unpaired Translation from Simulated to Realistic Ultrasound Images

2021-03-09 · Devavrat Tomar, Lin Zhang, Tiziano Portenier, Orcun Goksel

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…

DisentanglementTranslation

Efficient Unpaired Image Dehazing with Cyclic Perceptual-Depth Supervision

2020-07-10 · Chen Liu, Jiaqi Fan, Guosheng Yin

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 Dehazing

One-to-one Mapping for Unpaired Image-to-image Translation

2019-09-09 · Zengming Shen, S. Kevin Zhou, Yi-fan Chen, Bogdan Georgescu 외

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 TranslationTranslation

A Strictly Bounded Deep Network for Unpaired Cyclic Translation of Medical Images

2023-11-04 · Swati Rai, Jignesh S. Bhatt, Sarat Kumar Patra

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 NetworkTranslation

Generative Landmarks

2021-04-08 · David Ferman, Gaurav Bharaj

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