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.
@article{arxiv.1906.04913,
title = {Recurrent U-Net for Resource-Constrained Segmentation},
author = {Wei Wang and Kaicheng Yu and Joachim Hugonot and Pascal Fua and Mathieu Salzmann},
journal= {arXiv preprint arXiv:1906.04913},
year = {2019}
}
Comments
arXiv admin note: substantial text overlap with arXiv:1811.10914