Image Semantic Segmentation Method Based on Deep Fusion Network and Conditional Random Field

<div>Comparison of P-R curves between the proposed method and other methods. (a) The target scale is [0, 64] pixels. (b) The target scale is [64,192] pixels. (c) The target scale is [192, 500] pixels. (d) The target scale is [0, 500] pixels.</div>

Computational Intelligence and Neuroscience

fig4

Figure 4

Figure 4: Image Semantic Segmentation Method Based on Deep Fusion Network and Conditional Random Field 