Duplex Contextual Relation Network for Polyp Segmentation. (arXiv:2103.06725v3 [eess.IV] UPDATED)

Polyp segmentation is of great importance in the early diagnosis and
treatment of colorectal cancer. Since polyps vary in their shape, size, color,
and texture, accurate polyp segmentation is very challenging. One promising way
to mitigate the diversity of polyps is to model the contextual relation for
each pixel such as using attention mechanism. However, previous methods only
focus on learning the dependencies between the position within an individual
image and ignore the contextual relation across different images. In this …

arxiv network segmentation