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

@article{Xu2018AttnGANFT,
  title={AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks},
  author={T. Xu and Pengchuan Zhang and Qiuyuan Huang and Han Zhang and Zhe Gan and Xiaolei Huang and X. He},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={1316-1324}
}
  • T. Xu, Pengchuan Zhang, +4 authors X. He
  • Published 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
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. [...] Key Method 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…Expand
Text-to-Clipart using AttnGAN
Attn-Eh ALN: complex text-to-image generation with attention-enhancing adversarial learning networks
SemGAN: Text to Image Synthesis from Text Semantics using Attentional Generative Adversarial Networks
CAGAN: Text-To-Image Generation with Combined Attention GANs
Object-Driven Text-To-Image Synthesis via Adversarial Training
Semantically Consistent Hierarchical Text to Fashion Image Synthesis with an Enhanced-Attentional Generative Adversarial Network
Dualattn-GAN: Text to Image Synthesis With Dual Attentional Generative Adversarial Network
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 46 REFERENCES
A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
Photographic Text-to-Image Synthesis with a Hierarchically-Nested Adversarial Network
StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
Learning What and Where to Draw
Generative Adversarial Text to Image Synthesis
Conditional Image Generation with PixelCNN Decoders
Attention is All you Need
Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
Learning Deep Representations of Fine-Grained Visual Descriptions
...
1
2
3
4
5
...