DTGAN: Dual Attention Generative Adversarial Networks for Text-to-Image Generation

by   Zhenxing Zhang, et al.

Most existing text-to-image generation methods adopt a multi-stage modular architecture which has three significant problems: (1) Training multiple networks can increase the run time and affect the convergence and stability of the generative model; (2) These approaches ignore the quality of early-stage generator images; (3) Many discriminators need to be trained. To this end, we propose the Dual Attention Generative Adversarial Network (DTGAN) which can synthesize high quality and visually realistic images only employing a single generator/discriminator pair. The proposed model introduces channel-aware and pixel-aware attention modules that can guide the generator to focus on text-relevant channels and pixels based on the global sentence vector and to fine-tune original feature maps using attention weights. Also, Conditional Adaptive Instance-Layer Normalization (CAdaILN) is presented to help our attention modules flexibly control the amount of change in shape and texture by the input natural-language description. Furthermore, a new type of visual loss is utilized to enhance the image quality by ensuring the vivid shape and the perceptually uniform color distributions of generated images. Experimental results on benchmark datasets demonstrate the superiority of our proposed method compared to the state-of-the-art models with a multi-stage framework. Visualization of the attention maps shows that the channel-aware attention module is able to localize the discriminative regions, while the pixel-aware attention module has the ability to capture the globally visual contents for the generation of an image.



There are no comments yet.


page 13

page 14

page 15


DiverGAN: An Efficient and Effective Single-Stage Framework for Diverse Text-to-Image Generation

In this paper, we present an efficient and effective single-stage framew...

MirrorGAN: Learning Text-to-image Generation by Redescription

Generating an image from a given text description has two goals: visual ...

Controllable Text-to-Image Generation

In this paper, we propose a novel controllable text-to-image generative ...

DF-GAN: Deep Fusion Generative Adversarial Networks for Text-to-Image Synthesis

Synthesizing high-resolution realistic images from text descriptions is ...

Spatially Constrained Generative Adversarial Networks for Conditional Image Generation

Image generation has raised tremendous attention in both academic and in...

Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language

This paper addresses the problem of manipulating images using natural la...

cGANs with Conditional Convolution Layer

Conditional generative adversarial networks (cGANs) have been widely res...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.