Detail publikace

Denoise pre-training for segmentation neural networks

KOLAŘÍK, M.

Originální název

Denoise pre-training for segmentation neural networks

Anglický název

Denoise pre-training for segmentation neural networks

Jazyk

en

Originální abstrakt

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.

Anglický abstrakt

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.

Dokumenty

BibTex


@inproceedings{BUT157996,
  author="Martin {Kolařík}",
  title="Denoise pre-training for segmentation neural networks",
  annote="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.",
  address="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  booktitle="Proceedings of the 25th Conference STUDENT EEICT 2019",
  chapter="157996",
  howpublished="online",
  institution="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  year="2019",
  month="april",
  pages="739--744",
  publisher="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  type="conference paper"
}