Name
Abstract | ||
|---|---|---|
This study investigates a curriculum-style strategy for semi-supervised CNN segmentation, which devises a regression network to learn image-level information such as the size of the target region. These regressions are used to effectively regularize the segmentation network, constraining the softmax predictions of the unlabeled images to match the inferred label distributions. Our framework is based on inequality constraints, which tolerate uncertainties in the inferred knowledge, e.g., regressed region size. It can be used for a large variety of region attributes. We evaluated our approach for left ventricle segmentation in magnetic resonance images (MRI), and compared it to standard proposal-based semi-supervision strategies. Our method achieves competitive results, leveraging unlabeled data in a more efficient manner and approaching full-supervision performance. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1007/978-3-030-32245-8_63 | Lecture Notes in Computer Science |
Keywords | DocType | Volume |
Image segmentation,Semi-supervised learning,Constrained CNNs | Conference | 11765 |
ISSN | Citations | PageRank |
0302-9743 | 1 | 0.35 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hoel Kervadec | 1 | 25 | 2.94 |
| Dolz Jose | 2 | 91 | 16.76 |
| E Granger | 3 | 62 | 7.10 |
| Ismail Ben Ayed | 4 | 678 | 52.28 |