Abstract | ||
---|---|---|
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 [33], 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. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ICCV.2019.00223 | 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) |
Field | DocType | Volume |
Computer vision,Pattern recognition,Segmentation,Computer science,Artificial intelligence | Journal | abs/1906.04913 |
Issue | ISSN | Citations |
1 | 1550-5499 | 2 |
PageRank | References | Authors |
0.37 | 10 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wei Wang | 1 | 131 | 14.16 |
Kaicheng Yu | 2 | 4 | 1.41 |
Joachim Hugonot | 3 | 18 | 1.21 |
Pascal Fua | 4 | 12768 | 731.45 |
Mathieu Salzmann | 5 | 1578 | 88.48 |