WaveletNet: Logarithmic Scale Efficient Convolutional Neural Networks for Edge Devices

2018/11/28 by Jing, Li, Dangovski, Rumen, Soljacic, Marin
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1811.11644

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.

Related

• Wavelet based edge feature enhancement for convolutional neural networks
• EdgeCNN: Convolutional Neural Network Classification Model with small inputs for Edge Computing
• ANTNets: Mobile Convolutional Neural Networks for Resource Efficient Image Classification
• ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
• ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions