Using AAEHS-Net as an Attention-Based Auxiliary Extraction and Hybrid Subsampled Network for Semantic Segmentation

Figure 20

Segmentation results on the Massachusetts buildings dataset. (a) Image, (b) mask, (c) MHSU-Net, (d) HAD-ResUNet, (e) MR-UNet, (f) CE-UNet, and (g) AAEHS-Net.

(a)

(b)

(c)

(d)

(e)

(f)

(g)