Decom-UNet3+: A Retinal Vessel Segmentation Method Optimized With Decomposed Convolutions

The intricate and highly branched structure of retinal blood vessels, along with the fragility of fine vessels, makes segmentation a challenging task. To address this issue, we propose Decom-UNet3+, a model that optimizes the encoders by employing decomposed convolutions. Specifically, the encoders...

Full description

Bibliographic Details

Published in:	IEEE Access
Main Authors:	Qun Li, Juntao Zhang, Licheng Hua, Songyin Fu, Chenjie Gu
Format:	Article
Language:	English
Published:	IEEE 2025-01-01
Subjects:	Attention mechanisms feature extraction multi-layer neural networks retinal vessels semantic segmentation
Online Access:	https://ieeexplore.ieee.org/document/11078270/