AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks

Authors:
  • TXTao Xu
    Tao Xu
  • PZPengchuan Zhang
    Pengchuan Zhang
  • QHQiuyuan Huang
    Qiuyuan Huang
  • HZHan Zhang
    Han Zhang
  • ZGZhe Gan
    Zhe Gan
  • XHXiaolei Huang
    Xiaolei Huang
  • XHXiaodong He
    Xiaodong He
Top Cited Papers
Publisher website
Google Scholar
Abstract
In this paper, we propose an Attentional Generative Adversarial Network (AttnGAN) that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation. With a novel attentional generative network, the AttnGAN can synthesize fine-grained details at different sub-regions of the image by paying attentions to the relevant words in the natural language description. In addition, a deep attentional multimodal similarity model is proposed to compute a fine-grained image-text matching loss for training the generator. The proposed AttnGAN significantly outperforms the previous state of the art, boosting the best reported inception score by 14.14% on the CUB dataset and 170.25% on the more challenging COCO dataset. A detailed analysis is also performed by visualizing the attention layers of the AttnGAN. It for the first time shows that the layered attentional GAN is able to automatically select the condition at the word level for generating different parts of the image.

This publication has 20 references indexed in Scilit: