中文
相关论文

相关论文: Guiding the One-to-one Mapping in CycleGAN via Opt…

200 篇论文

Learning inter-domain mappings from unpaired data can improve performance in structured prediction tasks, such as image segmentation, by reducing the need for paired data. CycleGAN was recently proposed for this problem, but critically…

机器学习 · 计算机科学 2018-06-20 Amjad Almahairi , Sai Rajeswar , Alessandro Sordoni , Philip Bachman , Aaron Courville

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 extensions to multiple…

计算机视觉与模式识别 · 计算机科学 2020-01-16 Zengming Shen , S. Kevin Zhou , Yifan Chen , Bogdan Georgescu , Xuqi Liu , Thomas S. Huang

Unpaired image-to-image translation has attracted significant interest due to the invention of CycleGAN, a method which utilizes a combination of adversarial and cycle consistency losses to avoid the need for paired data. It is known that…

机器学习 · 计算机科学 2020-01-27 Nikita Moriakov , Jonas Adler , Jonas Teuwen

Recent advances in large-scale optimal transport have greatly extended its application scenarios in machine learning. However, existing methods either not explicitly learn the transport map or do not support general cost function. In this…

计算机视觉与模式识别 · 计算机科学 2020-03-17 Guansong Lu , Zhiming Zhou , Jian Shen , Cheng Chen , Weinan Zhang , Yong Yu

In this paper, we focus on analyzing the excess risk of the unpaired data generation model, called CycleGAN. Unlike classical GANs, CycleGAN not only transforms data between two unpaired distributions but also ensures the mappings are…

机器学习 · 计算机科学 2025-09-23 Luwei Sun , Dongrui Shen , Han Feng

Unpaired image-to-image translation has broad applications in art, design, and scientific simulations. One early breakthrough was CycleGAN that emphasizes one-to-one mappings between two unpaired image domains via generative-adversarial…

计算机视觉与模式识别 · 计算机科学 2022-10-19 Dmitrii Torbunov , Yi Huang , Haiwang Yu , Jin Huang , Shinjae Yoo , Meifeng Lin , Brett Viren , Yihui Ren

CycleGAN provides a framework to train image-to-image translation with unpaired datasets using cycle consistency loss [4]. While results are great in many applications, the pixel level cycle consistency can potentially be problematic and…

计算机视觉与模式识别 · 计算机科学 2024-11-25 Tongzhou Wang , Yihan Lin

To improve the performance of classical generative adversarial network (GAN), Wasserstein generative adversarial networks (W-GAN) was developed as a Kantorovich dual formulation of the optimal transport (OT) problem using Wasserstein-1…

计算机视觉与模式识别 · 计算机科学 2020-09-01 Byeongsu Sim , Gyutaek Oh , Jeongsol Kim , Chanyong Jung , Jong Chul Ye

Unsupervised image-to-image translation methods such as CycleGAN learn to convert images from one domain to another using unpaired training data sets from different domains. Unfortunately, these approaches still require centrally collected…

计算机视觉与模式识别 · 计算机科学 2021-06-18 Joonyoung Song , Jong Chul Ye

This paper presents a novel two-step approach for the fundamental problem of learning an optimal map from one distribution to another. First, we learn an optimal transport (OT) plan, which can be thought as a one-to-many map between the two…

The recent direction of unpaired image-to-image translation is on one hand very exciting as it alleviates the big burden in obtaining label-intensive pixel-to-pixel supervision, but it is on the other hand not fully satisfactory due to the…

计算机视觉与模式识别 · 计算机科学 2019-02-27 Rui Zhang , Tomas Pfister , Jia Li

The original publication Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks served as the inspiration for this implementation project. Researchers developed a novel method for doing image-to-image translations…

计算机视觉与模式识别 · 计算机科学 2022-08-16 Sai Pavan Tadem

We propose a parallel-data-free voice-conversion (VC) method that can learn a mapping from source to target speech without relying on parallel data. The proposed method is general purpose, high quality, and parallel-data free and works…

机器学习 · 统计学 2017-12-21 Takuhiro Kaneko , Hirokazu Kameoka

Optimal transport maps define a one-to-one correspondence between probability distributions, and as such have grown popular for machine learning applications. However, these maps are generally defined on empirical observations and cannot be…

统计理论 · 数学 2021-02-18 Lucas de Lara , Alberto González-Sanz , Jean-Michel Loubes

Recent years have witnessed a flurry of research activity in graph matching, which aims at finding the correspondence of nodes across two graphs and lies at the heart of many artificial intelligence applications. However, matching…

机器学习 · 计算机科学 2021-12-21 Weijie Liu , Hui Qian , Chao Zhang , Jiahao Xie , Zebang Shen , Nenggan Zheng

Recent techniques built on Generative Adversarial Networks (GANs), such as Cycle-Consistent GANs, are able to learn mappings among different domains built from unpaired datasets, through min-max optimization games between generators and…

机器学习 · 计算机科学 2020-08-18 Haoran You , Yu Cheng , Tianheng Cheng , Chunliang Li , Pan Zhou

A general theory is provided delivering convergence of maximal cyclically monotone mappings containing the supports of coupling measures of sequences of pairs of possibly random probability measures on Euclidean space. The theory is based…

统计理论 · 数学 2022-08-05 Johan Segers

Image translation is a burgeoning field in computer vision where the goal is to learn the mapping between an input image and an output image. However, most recent methods require multiple generators for modeling different domain mappings,…

计算机视觉与模式识别 · 计算机科学 2020-04-20 Xiaoming Yu , Xing Cai , Zhenqiang Ying , Thomas Li , Ge Li

Polarimetric imaging, along with deep learning, has shown improved performances on different tasks including scene analysis. However, its robustness may be questioned because of the small size of the training datasets. Though the issue…

计算机视觉与模式识别 · 计算机科学 2022-06-16 Cyprien Ruffino , Rachel Blin , Samia Ainouz , Gilles Gasso , Romain Hérault , Fabrice Meriaudeau , Stéphane Canu

In this work, we propose a novel machine learning approach to compute the optimal transport map between two continuous distributions from their unpaired samples, based on the DeepParticle methods. The proposed method leads to a min-min…

机器学习 · 统计学 2025-07-01 Yingyuan Li , Aokun Wang , Zhongjian Wang
‹ 上一页 1 2 3 10 下一页 ›