A top-down manner-based DCNN architecture for semantic image segmentation
Fig 5
Examples that our method based on GS superpixels produced better results than the DeepLab-CRF model.
Different colors represent different classes. (a) Input image (b) Segmentation results from DeepLab-CRF (c) Segmentation results from DeepLab-CRF-GS (d) Segmentation results from DeepLab-CRF-GS-v2 (e) Ground truth.