Recurrent U-Net for Resource-Constrained Segmentation

Wei Wang, Kaicheng Yu, Joachim Hugonot, Pascal Fua, Mathieu Salzmann; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 2142-2151


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.

Related Material

[pdf] [supp]
author = {Wang, Wei and Yu, Kaicheng and Hugonot, Joachim and Fua, Pascal and Salzmann, Mathieu},
title = {Recurrent U-Net for Resource-Constrained Segmentation},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}