Dilated Convolutions with Lateral Inhibitions for Semantic Image Segmentation. (arXiv:2006.03708v5 [cs.CV] UPDATED)

Dilated convolutions are widely used in deep semantic segmentation models as
they can enlarge the filters' receptive field without adding additional weights
nor sacrificing spatial resolution. However, as dilated convolutional filters
do not possess positional knowledge about the pixels on semantically meaningful
contours, they could lead to ambiguous predictions on object boundaries. In
addition, although dilating the filter can expand its receptive field, the
total number of sampled pixels remains unchanged, which usually comprises a
small fraction of the receptive …

arxiv cv segmentation semantic