WaveletNet: Logarithmic Scale Efficient Convolutional Neural Networks for Edge Devices

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.

arXiv comment10 pages, 5 figures

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• Deep Residual Learning for Image Recognition
• MobileNetV2: Inverted Residuals and Linear Bottlenecks
• Densely Connected Convolutional Networks
• Going Deeper with Convolutions
• Rethinking the Inception Architecture for Computer Vision
• Xception: Deep Learning with Depthwise Separable Convolutions
• Interleaved Group Convolutions for Deep Neural Networks
• Deep Convolutional Neural Networks with Merge-and-Run Mappings
• IGCV$2$: Interleaved Structured Sparse Convolutional Neural Networks