DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
Zili Yi,Hao Zhang,Ping Tan,Minglun Gong +3 more
- 01 Oct 2017
- pp 2868-2876
TL;DR: DualGAN as mentioned in this paper learns to translate images from domain U to those in domain V, while the dual GAN learns to invert the task, which enables image translators to be trained from two sets of unlabeled images from two domains.
read more
Abstract: Conditional Generative Adversarial Networks (GANs) for cross-domain image-to-image translation have made much progress recently [7, 8, 21, 12, 4, 18]. Depending on the task complexity, thousands to millions of labeled image pairs are needed to train a conditional GAN. However, human labeling is expensive, even impractical, and large quantities of data may not always be available. Inspired by dual learning from natural language translation [23], we develop a novel dual-GAN mechanism, which enables image translators to be trained from two sets of unlabeled images from two domains. In our architecture, the primal GAN learns to translate images from domain U to those in domain V, while the dual GAN learns to invert the task. The closed loop made by the primal and dual tasks allows images from either domain to be translated and then reconstructed. Hence a loss function that accounts for the reconstruction error of images can be used to train the translators. Experiments on multiple image translation tasks with unlabeled data show considerable performance gain of DualGAN over a single GAN. For some tasks, DualGAN can even achieve comparable or slightly better results than conditional GAN trained on fully labeled data.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Evolution and effectiveness of loss functions in generative adversarial networks
TL;DR: A detailed survey of the loss functions used in GANs can be found in this article, where the authors provide a critical analysis on the pros and cons of these loss functions.
7
•Posted Content
Risk Bounds for Unsupervised Cross-Domain Mapping with IPMs
TL;DR: A novel risk bound is derived, which upper bounds the risk between the learned mapping $h$ and the target mapping $y$ by a sum of three terms, and leads to multiple algorithmic consequences, including a method for hyperparameters selection and for early stopping in cross-domain mapping GANs.
7
Single Domain Generalization Method for Remote Sensing Image Segmentation via Category Consistency on Domain Randomization
Chenbin Liang,Weibin Li,Yunyun Dong,WenLin Fu +3 more
TL;DR: In comparison to other state-of-the-art SDG methods, CCDR can synthesize the more effective auxiliary domain, and perform more reliable classification on the unseen target domains without the sophisticated training pipeline and cumbersome data generation process.
7
•Posted Content
Exocentric to Egocentric Image Generation via Parallel Generative Adversarial Network
TL;DR: Zhang et al. as discussed by the authors proposed a parallel GAN with a cross-cycle loss to learn the shared information for generating egocentric images from exocentric view and incorporated a novel contextual feature loss in the learning procedure to capture the contextual information in images.
7
Learning to Generate Realistic Scene Chinese Character Images by Multitask Coupled GAN
Qingxiang Lin,Lingyu Liang,Yaoxiong Huang,Lianwen Jin +3 more
- 23 Nov 2018
TL;DR: Experiments show that the proposed MtC-GAN framework is general and flexible to improve the accuracy for SCCR and train the multitask networks using a new loss function that combines the constrains of encoders, generators and classifiers simultaneously.
7
References
U-Net: Convolutional Networks for Biomedical Image Segmentation
Olaf Ronneberger,Philipp Fischer,Thomas Brox +2 more
- 05 Oct 2015
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
- 08 Dec 2014
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Fully convolutional networks for semantic segmentation
Jonathan Long,Evan Shelhamer,Trevor Darrell +2 more
- 07 Jun 2015
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Image-to-Image Translation with Conditional Adversarial Networks
Phillip Isola,Jun-Yan Zhu,Tinghui Zhou,Alexei A. Efros +3 more
- 21 Jul 2017
TL;DR: Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks
Jun-Yan Zhu,Taesung Park,Phillip Isola,Alexei A. Efros +3 more
- 01 Oct 2017
TL;DR: CycleGAN as discussed by the authors learns a mapping G : X → Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss.
19.5K
Related Papers (5)
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
Diederik P. Kingma,Jimmy Ba +1 more
- 01 Jan 2015