WaveletNet: Logarithmic Scale Efficient Convolutional Neural Networks for Edge Devices
Machine Learning
2018-11-29 v1 Computer Vision and Pattern Recognition
Machine Learning
Abstract
We present a logarithmic-scale efficient convolutional neural network architecture for edge devices, named WaveletNet. Our model is based on the well-known depthwise convolution, and on two new layers, which we introduce in this work: a wavelet convolution and a depthwise fast wavelet transform. By breaking the symmetry in channel dimensions and applying a fast algorithm, WaveletNet shrinks the complexity of convolutional blocks by an O(logD/D) factor, where D is the number of channels. Experiments on CIFAR-10 and ImageNet classification show superior and comparable performances of WaveletNet compared to state-of-the-art models such as MobileNetV2.
Cite
@article{arxiv.1811.11644,
title = {WaveletNet: Logarithmic Scale Efficient Convolutional Neural Networks for Edge Devices},
author = {Li Jing and Rumen Dangovski and Marin Soljacic},
journal= {arXiv preprint arXiv:1811.11644},
year = {2018}
}
Comments
10 pages, 5 figures