基于生成对抗网络的文本两阶段生成高质量图像方法

曹寅,秦俊平,高彤,马千里,任家琪

Generative adversarial network based two-stage generation of high-quality images from text

Yin CAO,Junping QIN,Tong GAO,Qianli MA,Jiaqi REN

表 1 文本生成图像方法在2个数据集上的评价指标对比

Tab.1 Comparison of evaluation indexes of text-to-image generation methods in two datasets

模型 CUB COCO IS FID FID StackGAN[6] 3.70 35.51 74.05 StackGAN++[6] 3.84 — — AttnGAN[2] 4.36 24.37 35.49 MirrorGAN[8] 4.56 18.34 34.71 textStyleGAN[28] 4.78 — — DM-GAN[29] 4.75 16.09 32.64 SD-GAN[30] 4.67 — — DF-GAN[8] 5.10 14.81 19.32 SSA-GAN[31] 5.17 15.61 19.37 RAT-GAN[32] 5.36 13.91 14.60 CogView2[33] — — 17.70 KNN-Diffusion[16] — — 16.66 DFA-GAN-第一阶段 4.53 16.07 25.09 DFA-GAN-第二阶段 5.34 10.96 19.17