paper-with-me

Papers

WaveletNet: Logarithmic Scale Efficient Convolutional Neural Networks for Edge Devices

2018-11-28 · Li Jing, Rumen Dangovski, Marin Soljacic

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.

📄 PDF Abstract BibTeX arXiv:1811.11644

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification

Methods 이 논문이 사용한 방법론

Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Inverted Residual Block 설명 없음
Average Pooling 설명 없음
Tether Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Convolutional Neural Networks using Logarithmic Data Representation

2016-03-03 · Daisuke Miyashita, Edward H. Lee, Boris Murmann

Recent advances in convolutional neural networks have considered model complexity and hardware efficiency to enable deployment onto embedded systems and mobile devices. For example, it is now well-known that the arithmet…

General Classification

Energy Efficient Hardware Acceleration of Neural Networks with Power-of-Two Quantisation

2022-09-30 · Dominika Przewlocka-Rus, Tomasz Kryjak

Deep neural networks virtually dominate the domain of most modern vision systems, providing high performance at a cost of increased computational complexity.Since for those systems it is often required to operate both in…

Autonomous Vehicles

HarmoF0: Logarithmic Scale Dilated Convolution For Pitch Estimation

2022-05-02 · Weixing Wei, Peilin Li, Yi Yu, Wei Li

Sounds, especially music, contain various harmonic components scattered in the frequency dimension. It is difficult for normal convolutional neural networks to observe these overtones. This paper introduces a multiple ra…

Atrial Fibrillation Detection Using Weight-Pruned, Log-Quantised Convolutional Neural Networks

2022-06-14 · Xiu Qi Chang, Ann Feng Chew, Benjamin Chen Ming Choong, Shuhui Wang 외

Deep neural networks (DNN) are a promising tool in medical applications. However, the implementation of complex DNNs on battery-powered devices is challenging due to high energy costs for communication. In this work, a c…

Atrial Fibrillation DetectionModel Compression

A Very Compact Embedded CNN Processor Design Based on Logarithmic Computing

2020-10-13 · Tsung-Ying Lu, Hsu-Hsun Chin, Hsin-I Wu, Ren-Song Tsay

In this paper, we propose a very compact embedded CNN processor design based on a modified logarithmic computing method using very low bit-width representation. Our high-quality CNN processor can easily fit into edge dev…

Edge-computingimage-classificationImage Classificationobject-detection+1