Denoise Pre-Training For Segmentation Neural Networks
| but.event.date | 25.04.2019 | cs |
| but.event.title | Student EEICT 2019 | cs |
| dc.contributor.author | Kolarik, Martin | |
| dc.date.accessioned | 2020-04-16T07:19:41Z | |
| dc.date.available | 2020-04-16T07:19:41Z | |
| dc.date.issued | 2019 | cs |
| dc.description.abstract | This paper proposes a method for pre-training segmentation neural networks on small datasets using unlabelled training data with added noise. The pre-training process helps the network with initial better weights settings for the training itself and also augments the training dataset when dealing with small labelled datasets especially in medical imaging. The experiment comparing results of pre-trained and not pre-trained networks on MRI brain segmentation task has shown that the denoise pre-training helps the network with faster training convergence without overfitting and achieving better results in all compared metrics even on very small datasets. | en |
| dc.format | text | cs |
| dc.format.extent | 739-743 | cs |
| dc.format.mimetype | application/pdf | en |
| dc.identifier.citation | Proceedings of the 25st Conference STUDENT EEICT 2019. s. 739-743. ISBN 978-80-214-5735-5 | cs |
| dc.identifier.isbn | 978-80-214-5735-5 | |
| dc.identifier.uri | http://hdl.handle.net/11012/186770 | |
| dc.language.iso | en | cs |
| dc.publisher | Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií | cs |
| dc.relation.ispartof | Proceedings of the 25st Conference STUDENT EEICT 2019 | en |
| dc.relation.uri | http://www.feec.vutbr.cz/EEICT/ | cs |
| dc.rights | © Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií | cs |
| dc.rights.access | openAccess | en |
| dc.subject | deep learning | en |
| dc.subject | denoising | en |
| dc.subject | neural network | en |
| dc.subject | pre-training | en |
| dc.subject | segmentation | en |
| dc.title | Denoise Pre-Training For Segmentation Neural Networks | en |
| dc.type.driver | conferenceObject | en |
| dc.type.status | Peer-reviewed | en |
| dc.type.version | publishedVersion | en |
| eprints.affiliatedInstitution.department | Fakulta elektrotechniky a komunikačních technologií | cs |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- 739_eeict2019.pdf
- Size:
- 1.16 MB
- Format:
- Adobe Portable Document Format
- Description: