Ghent University Academic Bibliography

Advanced

Convolutional neural network pruning to accelerate membrane segmentation in electron microscopy

Joris Roels UGent, Jonas De Vylder, Jan Aelterman UGent, Yvan Saeys UGent and Wilfried Philips UGent (2017) 2017 IEEE 14th international symposium on biomedical imaging (ISBI 2017). p.633-637
abstract
Biological membranes are one of the most basic structures and regions of interest in cell biology. In the study of membranes, segment extraction is a well-known and difficult problem because of impeding noise, directional and thickness variability, etc. Recent advances in electron microscopy membrane segmentation are able to cope with such difficulties by training convolutional neural networks. However, because of the massive amount of features that have to be extracted while propagating forward, the practical usability diminishes, even with state-of-the-art GPU's. A significant part of these network features typically contains redundancy through correlation and sparsity. In this work, we propose a pruning method for convolutional neural networks that ensures the training loss increase is minimized. We show that the pruned networks, after retraining, are more efficient in terms of time and memory, without significantly affecting the network accuracy. This way, we manage to obtain real-time membrane segmentation performance, for our specific electron microscopy setup.
Please use this url to cite or link to this publication:
author
organization
year
type
conference (other)
publication status
published
subject
in
2017 IEEE 14th international symposium on biomedical imaging (ISBI 2017)
pages
633 - 637
publisher
IEEE
place of publication
New York, NY, USA
conference name
14th International symposium on Biomedical Imaging (ISBI 2017)
conference location
Melbourne, VIC, Australia
conference start
2017-04-18
conference end
2017-04-21
ISBN
9781509011728
DOI
10.1109/isbi.2017.7950600
language
English
UGent publication?
yes
classification
C1
copyright statement
I have transferred the copyright for this publication to the publisher
id
8528682
handle
http://hdl.handle.net/1854/LU-8528682
date created
2017-08-10 15:55:46
date last changed
2017-08-31 14:38:57
@inproceedings{8528682,
  abstract     = {Biological membranes are one of the most basic structures and regions of interest in cell biology. In the study of membranes, segment extraction is a well-known and difficult problem because of impeding noise, directional and thickness variability, etc. Recent advances in electron microscopy membrane segmentation are able to cope with such difficulties by training convolutional neural networks. However, because of the massive amount of features that have to be extracted while propagating forward, the practical usability diminishes, even with state-of-the-art GPU's. A significant part of these network features typically contains redundancy through correlation and sparsity. In this work, we propose a pruning method for convolutional neural networks that ensures the training loss increase is minimized. We show that the pruned networks, after retraining, are more efficient in terms of time and memory, without significantly affecting the network accuracy. This way, we manage to obtain real-time membrane segmentation performance, for our specific electron microscopy setup.},
  author       = {Roels, Joris and De Vylder, Jonas and Aelterman, Jan and Saeys, Yvan and Philips, Wilfried},
  booktitle    = {2017 IEEE 14th international symposium on biomedical imaging (ISBI 2017)},
  isbn         = {9781509011728},
  language     = {eng},
  location     = {Melbourne, VIC, Australia},
  pages        = {633--637},
  publisher    = {IEEE},
  title        = {Convolutional neural network pruning to accelerate membrane segmentation in electron microscopy},
  url          = {http://dx.doi.org/10.1109/isbi.2017.7950600},
  year         = {2017},
}

Chicago
Roels, Joris, Jonas De Vylder, Jan Aelterman, Yvan Saeys, and Wilfried Philips. 2017. “Convolutional Neural Network Pruning to Accelerate Membrane Segmentation in Electron Microscopy.” In 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), 633–637. New York, NY, USA: IEEE.
APA
Roels, Joris, De Vylder, J., Aelterman, J., Saeys, Y., & Philips, W. (2017). Convolutional neural network pruning to accelerate membrane segmentation in electron microscopy. 2017 IEEE 14th international symposium on biomedical imaging (ISBI 2017) (pp. 633–637). Presented at the 14th International symposium on Biomedical Imaging (ISBI 2017), New York, NY, USA: IEEE.
Vancouver
1.
Roels J, De Vylder J, Aelterman J, Saeys Y, Philips W. Convolutional neural network pruning to accelerate membrane segmentation in electron microscopy. 2017 IEEE 14th international symposium on biomedical imaging (ISBI 2017). New York, NY, USA: IEEE; 2017. p. 633–7.
MLA
Roels, Joris, Jonas De Vylder, Jan Aelterman, et al. “Convolutional Neural Network Pruning to Accelerate Membrane Segmentation in Electron Microscopy.” 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017). New York, NY, USA: IEEE, 2017. 633–637. Print.