WaveletNet: Logarithmic Scale Efficient Convolutional Neural Networks for Edge Devices
This work addresses the need for efficient neural networks on resource-constrained edge devices, representing an incremental improvement over existing methods like depthwise convolution.
The authors tackled the problem of efficient convolutional neural networks for edge devices by introducing WaveletNet, which reduces computational complexity by an O(logD/D) factor and achieves superior or comparable performance to MobileNetV2 on CIFAR-10 and ImageNet.
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.