Efficient convolutional neural networks for pixelwise classification on heterogeneous hardware systems.

janelia7_blocks-janelia7_biblio_header | block

IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro. 2016 Jun 15;. doi: 10.1109/ISBI.2016.7493487

Efficient convolutional neural networks for pixelwise classification on heterogeneous hardware systems. Turaga LabFunke Lab

Tschopp F, Martel JN, Turaga SC, Cook M, Funke J

Download the PDF

janelia7_blocks-janelia7_biblio_abstract | block

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 (œ 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 57×, maintaining identical prediction results.

node:body | entity_field

Main Menu (Mobile)- Block

Main Menu - Block

Efficient convolutional neural networks for pixelwise classification on heterogeneous hardware systems.

Abstract

Janelia Authors