Header

UZH-Logo

Maintenance Infos

Efficient convolutional neural networks for pixelwise classification on heterogeneous hardware systems


Tschopp, Fabian; Martel, Julien N P; Turaga, Srinivas C; Cook, Matthew; Funke, Jan (2016). Efficient convolutional neural networks for pixelwise classification on heterogeneous hardware systems. In: The International Symposium on Biomedical Imaging (ISBI) 2016, Melbourne, Australia, 13 April 2016 - 16 April 2016.

Abstract

With recent advances in high-throughput Electron Microscopy (EM) imaging it is now possible to image an entire nervous system of organisms like Drosophila melanogaster. One of the bottlenecks to reconstruct a connectome from these large volumes (approx. 100 TiB) is the pixel-wise prediction of membranes. The time it would typically take to process such a volume using a convolutional neural network (CNN) with a sliding window approach is in the order of years on a current GPU. With sliding windows, however, a lot of redundant computations are carried out. In this paper, we present an extension to the Caffe library to increase throughput by predicting many pixels at once. On a sliding window network successfully used for membrane classification, we show that our method achieves a speedup of up to 57x, maintaining identical prediction results.

Abstract

With recent advances in high-throughput Electron Microscopy (EM) imaging it is now possible to image an entire nervous system of organisms like Drosophila melanogaster. One of the bottlenecks to reconstruct a connectome from these large volumes (approx. 100 TiB) is the pixel-wise prediction of membranes. The time it would typically take to process such a volume using a convolutional neural network (CNN) with a sliding window approach is in the order of years on a current GPU. With sliding windows, however, a lot of redundant computations are carried out. In this paper, we present an extension to the Caffe library to increase throughput by predicting many pixels at once. On a sliding window network successfully used for membrane classification, we show that our method achieves a speedup of up to 57x, maintaining identical prediction results.

Statistics

Citations

Dimensions.ai Metrics
2 citations in Web of Science®
2 citations in Scopus®
9 citations in Microsoft Academic
Google Scholar™

Altmetrics

Downloads

0 downloads since deposited on 27 Jan 2017
0 downloads since 12 months

Additional indexing

Item Type:Conference or Workshop Item (Speech), refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Event End Date:16 April 2016
Deposited On:27 Jan 2017 11:22
Last Modified:23 Aug 2018 07:08
Publisher:Proceedings of 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI)
Series Name:IEEE ISBI
OA Status:Closed
Publisher DOI:https://doi.org/10.1109/ISBI.2016.7493487
Official URL:http://ieeexplore.ieee.org/document/7493487/

Download