Approximating Continuous Convolutions for Deep Network Compression
This addresses model size reduction for deep learning applications, offering a novel approach that is incremental but compatible with other compression methods.
The paper tackles the problem of compressing convolutional neural networks by reframing discrete convolution as continuous convolution, achieving a 50% reduction in model size with only a 1.86% accuracy loss.
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.