U-Net with Hierarchical Bottleneck Attention for Landmark Detection in Fundus Images of the Degenerated Retina

1 code implementation • 9 Jul 2021 • Shuyun Tang, Ziming Qi, Jacob Granley, Michael Beyeler

The network consists of a novel bottleneck attention block that combines and refines self-attention, channel attention, and relative-position attention to highlight retinal abnormalities that may be important for fovea and OD segmentation in the degenerated retina.

Fovea Detection Optic Disc Detection +2