swMATH ID: 42519
Software Authors: Tao Xu, Pengchuan Zhang, Qiuyuan Huang, Han Zhang, Zhe Gan, Xiaolei Huang, Xiaodong He
Description: AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks. 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 subregions 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
Homepage: https://arxiv.org/abs/1711.10485
Source Code:  https://github.com/taoxugit/AttnGAN
Related Software: BigGAN; Wasserstein GAN; CIFAR; Python; StackGAN; InfoGAN; MMD GAN; sngan_projection; StarGAN; ImageNet; StyleGAN; LR-GAN; Dist-GAN; U-Net; DARTS; Auto-DeepLab; Adam; MGAN; ProbGAN; AutoGAN
Cited in: 3 Documents

Citations by Year