CVOct 23, 2018

Convolutional Neural Network Pruning to Accelerate Membrane Segmentation in Electron Microscopy

arXiv:1810.09735v12 citations
Originality Synthesis-oriented
AI Analysis

This work addresses efficiency issues in membrane segmentation for cell biology researchers, but it is incremental as it applies an existing pruning technique to a specific domain.

The paper tackles the problem of slow membrane segmentation in electron microscopy by proposing a pruning method for convolutional neural networks, achieving real-time performance without significantly affecting accuracy.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes