基于多模态语义信息的文本生成图像方法
杨冰,周家辉,姚金良,向学勤

Text-to-image generation method based on multimodal semantic information
Bing YANG,Jiahui ZHOU,Jinliang YAO,Xueqin XIANG
表 4 语义对齐鉴别器的消融实验结果
Tab.4 Ablation experiment results of semantic alignment discriminator
语义对齐块数量FID↓SCLIP↑
110.180.3158
210.030.3174
39.970.3191
410.050.3185