基于Transformer的高效自适应语义分割网络

张海波,蔡磊,任俊平,王汝言,刘富

Efficient and adaptive semantic segmentation network based on Transformer

Hai-bo ZHANG,Lei CAI,Jun-ping REN,Ru-yan WANG,Fu LIU

表 6 联合重采样自注意力模块对EA-Former-T算法性能的影响

Tab.6 Influence of joint resampling self-attention module on algorithm performance of EA-Former-T

联合重采样 自注意力 降维 FPS/ （帧 $ \cdot {{\rm{s}}^{ - 1}} $） GFLOPs mIoU/ % × × 32.4 8.4 37.5 √ × 11.5 9.0 37.6 √ √ 51.1 7.1 38.1