Lightweight Real-Time Image Semantic Segmentation Network Based on Multi-Resolution Hybrid Attention Mechanism

Table 3

To verify the impact of fusion of different stage segmentation maps on the final accuracy of our network, we validate the mIoU results on the Cityscapes set.

Seg2	Seg3	Seg4	mIoU
✓			72.62
✓	✓		72.77(+0.15)
✓	✓	✓	72.83(+0.21)