PPANet: Point-Wise Pyramid Attention Network for Semantic Segmentation

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2021/5563875/figures/5563875.fig.004a.svgz" name="5563875.fig.004a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Without mathematical morphology</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2021/5563875/figures/5563875.fig.004b.svgz" name="5563875.fig.004b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>With mathematical morphology</td></tr></table>

<div>Comparison between PPANet (a) without mathematical morphology and (b) with mathematical morphology. In the first picture, some pixels belong to nonroad classified as a road.</div>

Wireless Communications and Mobile Computing

fig4

Figure 4

Figure 4: PPANet: Point-Wise Pyramid Attention Network for Semantic Segmentation 