| First Authors | Tim-Oliver Buchholz |
|---|---|
| Authors | Tim-Oliver Buchholz, Mangal Prakash, Deborah Schmidt, Alexander Krull, Florian Jug |
| Corresponding Authors | Florian Jug |
| Last Authors | Florian Jug |
| Conference Proceedings Volume Title | Computer vision - ECCV 2020 workshops : Glasgow, UK, August 23-28, 2020 : proceedings : Part 1 |
| Series Title | (Lecture Notes in Computer Science ; 12535) |
| Conference Name | 16th european conference on COMPUTER VISION 23-28 August 2020 |
| Conference Location | online |
| Conference Start Date | 2020-08-23 |
| Conference End Date | 2020-08-28 |
| Chapter Number | |
| Publisher | Springer International Publishing |
| Conference Proceedings Editors | Adrien Bartoli |
| ISBN | 978-3-030-66414-5 |
| First Page | 324 |
| Last Page | 337 |
| Open Access | false |
| Print Publication Date | 2020-08-28 |
| Online Publication Date | 2020-08-28 |
| Abstract | Microscopy image analysis often requires the segmentation of objects, but training data for this task is typically scarce and hard to obtain. Here we propose DenoiSeg, a new method that can be trained end-to-end on only a few annotated ground truth segmentations. We achieve this by extending Noise2Void, a self-supervised denoising scheme that can be trained on noisy images alone, to also predict dense 3-class segmentations. The reason for the success of our method is that segmentation can profit from denoising, especially when performed jointly within the same network. The network becomes a denoising expert by seeing all available raw data, while co-learning to segment, even if only a few segmentation labels are available. This hypothesis is additionally fueled by our observation that the best segmentation results on high quality (very low noise) raw data are obtained when moderate amounts of synthetic noise are added. This renders the denoising-task non-trivial and unleashes the desired co-learning effect. We believe that DenoiSeg offers a viable way to circumvent the tremendous hunger for high quality training data and effectively enables learning of dense segmentations when only very limited amounts of segmentation labels are available. |
| Cover Image | |
| Affiliated With | CSBD, Jug |
| Selected By | |
| Acknowledged Services | |
| Publication Status | Published |
| Edoc Link | |
| Sfx Link | |
| DOI | 10.1007/978-3-030-66415-2_21 |
| PubMed ID | |
| WebOfScience Link | |
| Alternative Full Text URL | |
| Display Publisher Download Only | false |
| Visible On MPI-CBG Website | true |
| PDF Downloadable | true |
| Created By | thuem |
| Added Date | 2022-02-16 |
| Last Edited By | herbst |
| Last Edited Date | 2022-03-03 17:30:35.785 |
| Library ID | 8287 |
| Document ID | |
| Entry Complete | true |
| eDoc Compliant | true |
| Include in Edoc Report | true |
| In Pure | true |
| Ready for eDoc Export | false |
| Author Affiliations Complete | false |
| Project Name | |
| Project URL | |
| Grant ID | |
| Funding Programme | |
| Funding Organisation |