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:
[Proceedings of ICCV 2019]
Presented at:
International Conference on Computer Vision (ICCV 2019), Seoul, Korea, Oct 27 - Nov 3, 2019
Year:
Oct 27 2019
Keywords:
Laboratories:




 Record created 2019-08-13, last modified 2019-08-14

Final:
Download fulltext
PDF

Rate this document:

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