AttnGAN 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 Publications all top 5 Cited by 11 Authors 1 Benaim, Sagie 1 Benny, Yaniv 1 Galanti, Tomer 1 Hou, Thomas Yizhao 1 Jiao, Jiantao 1 Lam, Ka Chun 1 Tse, David N. C. 1 Wolf, Lior 1 Zhang, Pengchuan 1 Zhang, Shumao 1 Zhu, Banghua Cited in 3 Serials 1 IEEE Transactions on Information Theory 1 Computational Mechanics 1 International Journal of Computer Vision Cited in 5 Fields 3 Computer science (68-XX) 2 Statistics (62-XX) 1 Calculus of variations and optimal control; optimization (49-XX) 1 Numerical analysis (65-XX) 1 Information and communication theory, circuits (94-XX) Citations by Year