How and why do state-of-the-art models in medical segmentation differ from general segmentation models?

Asked Jan 11 '21 at 15:10

Active Jan 12 '21 at 00:18

Viewed 66 times

I am just getting into medical image segmentation and have been able to understand the state-of-the-art architectures, like Double UNet, UNet++, and Multiresunet.

What I haven't understood yet: Why are these approaches better for medical segmentation than, for example, HRNet-OCR, which currently tops the rankings of the Cityscapes dataset, and vice versa?

edited Jan 12 '21 at 00:18

nbro

39,006
12
98
176

asked Jan 11 '21 at 15:10

Bert Gayus

Why do you think that UNet++ is better than HRNet-OCR? Can you please provide a reference that supports this conclusion? It may also be a good idea to include links to the papers that introduced all these models and to some site or whatever that supports this claim "HRNet-OCR, which currently tops the rankings of the Cityscapes dataset". – nbro Feb 01 '21 at 17:48

How and why do state-of-the-art models in medical segmentation differ from general segmentation models?

0 Answers0