Approximating Continuous Convolutions for Deep Network Compression
Theo W Costain (University Of Oxford),* Victor Adrian Prisacariu (University of Oxford)
The 33rd British Machine Vision Conference
Abstract
We present ApproxConv, a novel method for compressing the layers of a convolutional neural network. Reframing conventional discrete convolution as continuous convolution of parametrised functions over space, we use functional approximations to capture the essential structures of CNN filters with fewer parameters than conventional operations. Our method is able to reduce the size of trained CNN layers requiring only a small amount of fine-tuning. We show that our method is able to compress existing deep network models by half whilst losing only 1.86% accuracy. Further, we demonstrate that our method is compatible with other compression methods like quantisation allowing for further reductions in model size.Video
Citation
@inproceedings{Costain_2022_BMVC,
author = {Theo W Costain and Victor Adrian Prisacariu},
title = {Approximating Continuous Convolutions for Deep Network Compression},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0027.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by