Recurrent U-Net for Resource-Constrained Segmentation

State-of-the-art segmentation methods rely on very deep networks that are not always easy to train without very large training datasets and tend to be relatively slow to run on standard GPUs. In this paper, we introduce a novel recurrent U-Net architecture that preserves the compactness of the original U-Net, while substantially increasing its performance to the point where it outperforms the state of the art on several benchmarks. We will demonstrate its effectiveness for several tasks, including hand segmentation, retina vessel segmentation, and road segmentation. We also introduce a large-scale dataset for hand segmentation.


Published in:
2019 Ieee/Cvf International Conference On Computer Vision (Iccv 2019), 2142-2151
Presented at:
IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, SOUTH KOREA, Oct 27-Nov 02, 2019
Year:
Oct 27 2019
Publisher:
Los Alamitos, IEEE COMPUTER SOC
ISBN:
978-1-7281-4803-8
Keywords:
Laboratories:


Note: The status of this file is: Anyone


 Record created 2019-08-13, last modified 2020-10-25

Final:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)