基于Transformer的多模态级联文档布局分析网络
温绍杰,吴瑞刚,冯超文,刘英莉

Multimodal cascaded document layout analysis network based on Transformer
Shaojie WEN,Ruigang WU,Chaowen FENG,Yingli LIU
表 1 不同图像处理方法的参数量对比
Tab.1 Comparison of parameter sizes for different image processing methods
模型主干网络Np/106
ResNet-50CNN25
ResNet-101CNN44
ResNet-152CNN60
线性嵌入(本文方法)Linear0.6