Filter sharing: Efficient learning of parameters for volumetric convolutions

TL;DR

This paper introduces a filter sharing method that reduces CNN parameter complexity by deriving all filters from a small set during training, enabling effective 3D lung nodule segmentation with limited data.

Contribution

It proposes a novel filter sharing approach that exploits filter redundancy to decrease training parameters in volumetric CNNs, especially useful in data-scarce medical imaging.

Findings

Achieves comparable segmentation accuracy with fewer training examples.

Reduces the number of trainable parameters significantly.

Demonstrates effectiveness on 3D lung nodule segmentation.

Abstract

Typical convolutional neural networks (CNNs) have several millions of parameters and require a large amount of annotated data to train them. In medical applications where training data is hard to come by, these sophisticated machine learning models are difficult to train. In this paper, we propose a method to reduce the inherent complexity of CNNs during training by exploiting the significant redundancy that is noticed in the learnt CNN filters. Our method relies on finding a small set of filters and mixing coefficients to derive every filter in each convolutional layer at the time of training itself, thereby reducing the number of parameters to be trained. We consider the problem of 3D lung nodule segmentation in CT images and demonstrate the effectiveness of our method in achieving good results with only few training examples.