Feature-Grounded Single-Stage Text-to-Image Generation  

作　　者：Yuan Zhou Peng Wang Lei Xiang Haofeng Zhang 

机构地区：[1]School of Artificial Intelligence,Nanjing University of Information Science and Technology,Nanjing 210044,China [2]School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China

出　　处：《Tsinghua Science and Technology》2024年第2期469-480,共12页清华大学学报（自然科学版（英文版）

基　　金：supported by the National Natural Science Foundation of China(No.61872187).

摘　　要：Recently,Generative Adversarial Networks(GANs)have become the mainstream text-to-image(T2I)framework.However,a standard normal distribution noise of inputs cannot provide sufficient information to synthesize an image that approaches the ground-truth image distribution.Moreover,the multistage generation strategy results in complex T2I applications.Therefore,this study proposes a novel feature-grounded single-stage T2I model,which considers the“real”distribution learned from training images as one input and introduces a worst-case-optimized similarity measure into the loss function to enhance the model's generation capacity.Experimental results on two benchmark datasets demonstrate the competitive performance of the proposed model in terms of the Frechet inception distance and inception score compared to those of some classical and state-of-the-art models,showing the improved similarities among the generated image,text,and ground truth.

关 键 词：text-to-image(T2I) feature-grounded single-stage generation Generative Adversarial Network(GAN) 

分 类 号：TP309.7[自动化与计算机技术—计算机系统结构] TP183[自动化与计算机技术—计算机科学与技术]