Published on Thu Mar 28 2019

Attention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image Translation

Hao Tang, Dan Xu, Nicu Sebe, Yan Yan

Attention-Guided Generative Adversarial Network (AGGAN) can detect the most discriminative semantic object. The proposed AGGAN is trained by an end-to-end fashion. It is effective to generate sharper and more accurate images than existing models.

0
0
0
Abstract

The state-of-the-art approaches in Generative Adversarial Networks (GANs) are able to learn a mapping function from one image domain to another with unpaired image data. However, these methods often produce artifacts and can only be able to convert low-level information, but fail to transfer high-level semantic part of images. The reason is mainly that generators do not have the ability to detect the most discriminative semantic part of images, which thus makes the generated images with low-quality. To handle the limitation, in this paper we propose a novel Attention-Guided Generative Adversarial Network (AGGAN), which can detect the most discriminative semantic object and minimize changes of unwanted part for semantic manipulation problems without using extra data and models. The attention-guided generators in AGGAN are able to produce attention masks via a built-in attention mechanism, and then fuse the input image with the attention mask to obtain a target image with high-quality. Moreover, we propose a novel attention-guided discriminator which only considers attended regions. The proposed AGGAN is trained by an end-to-end fashion with an adversarial loss, cycle-consistency loss, pixel loss and attention loss. Both qualitative and quantitative results demonstrate that our approach is effective to generate sharper and more accurate images than existing models. The code is available at https://github.com/Ha0Tang/AttentionGAN.

Wed Nov 27 2019
Computer Vision
AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adversarial Networks
State-of-the-art methods in image-to-image translation are capable of learning a mapping from a source domain to a target domain with unpaired image data. The existing methods have achieved promising results, but still produce artifacts.
0
0
0
Mon Jun 14 2021
Computer Vision
Improved Transformer for High-Resolution GANs
Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation. In this paper, we introduce two key ingredients to Transformer to address this challenge.
2
13
62
Mon Feb 03 2020
Machine Learning
Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation
We propose a novel model named Multi-Channel Attention Selection Generative Adversarial Network (SelectionGAN) for guided image-to-image translation. The proposed SelectionGAN explicitly utilizes the semantic guidance information and consists of two stages.
0
0
0
Mon Aug 19 2019
Computer Vision
SPA-GAN: Spatial Attention GAN for Image-to-Image Translation
SPA-GAN is a lightweight model that does not need additional attention networks or supervision. Qualitative and quantitative comparison against state-of-the-art methods on benchmark datasets demonstrates the superior performance of SPA-GAN.
0
0
0
Mon May 21 2018
Machine Learning
Self-Attention Generative Adversarial Networks
SAGAN allows attention-driven, long-range dependency modeling for image generation tasks. Traditional convolutional GANs generate high-resolution details as a function of only spatially local points.
4
1
2
Sat Dec 14 2019
Machine Learning
Asymmetric Generative Adversarial Networks for Image-to-Image Translation
State-of-the-art models for unpaired image-to-image translation with Generative Adversarial Networks (GANs) can learn the mapping from the source domain to the target domain using a cycle-consistency loss. Existing methods adopt a symmetric network architecture to learn both forward andbackward cycles.
0
0
0