paper-with-me

Papers

ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions

2018-09-05 · NeurIPS 2018 12 · Hongyang Gao, Zhengyang Wang, Shuiwang Ji

Convolutional neural networks (CNNs) have shown great capability of solving various artificial intelligence tasks. However, the increasing model size has raised challenges in employing them in resource-limited applications. In this work, we propose to compress deep models by using channel-wise convolutions, which re- place dense connections among feature maps with sparse ones in CNNs. Based on this novel operation, we build light-weight CNNs known as ChannelNets. Channel- Nets use three instances of channel-wise convolutions; namely group channel-wise convolutions, depth-wise separable channel-wise convolutions, and the convolu- tional classification layer. Compared to prior CNNs designed for mobile devices, ChannelNets achieve a significant reduction in terms of the number of parameters and computational cost without loss in accuracy. Notably, our work represents the first attempt to compress the fully-connected classification layer, which usually accounts for about 25% of total parameters in compact CNNs. Experimental results on the ImageNet dataset demonstrate that ChannelNets achieve consistently better performance compared to prior methods.

📄 PDF Abstract BibTeX arXiv:1809.01330

Code (2)

HongyangGao/ChannelNets tf
osmr/imgclsmob mxnet

Tasks

General Classification

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Channel Compression: Rethinking Information Redundancy among Channels in CNN Architecture

2020-07-02 · Jinhua Liang, Tao Zhang, Guoqing Feng

Model compression and acceleration are attracting increasing attentions due to the demand for embedded devices and mobile applications. Research on efficient convolutional neural networks (CNNs) aims at removing feature …

Acoustic Scene ClassificationEvent Detectionimage-classificationImage Classification+3

LST-Net: Learning a Convolutional Neural Network with a Learnable Sparse Transform

2020-08-01 · ECCV 2020 8 · Lida Li, Kun Wang, Shuai Li, Xiangchu Feng 외

The 2D convolutional (Conv2d) layer is the fundamental element to a deep convolutional neural network (CNN). Despite the great success of CNN, the conventional Conv2d is still limited in effectively reducing the spatial …

Convolution with even-sized kernels and symmetric padding

2019-03-20 · NeurIPS 2019 12 · Shuang Wu, Guanrui Wang, Pei Tang, Feng Chen 외

Compact convolutional neural networks gain efficiency mainly through depthwise convolutions, expanded channels and complex topologies, which contrarily aggravate the training process. Besides, 3x3 kernels dominate the sp…

Continual Learningimage-classificationImage Classification

Dense Pruning of Pointwise Convolutions in the Frequency Domain

2021-09-16 · Mark Buckler, Neil Adit, Yuwei Hu, Zhiru Zhang 외

Depthwise separable convolutions and frequency-domain convolutions are two recent ideas for building efficient convolutional neural networks. They are seemingly incompatible: the vast majority of operations in depthwise …

Sensitivity

RecNets: Channel-wise Recurrent Convolutional Neural Networks

2019-05-28 · George Retsinas, Athena Elafrou, Georgios Goumas, Petros Maragos

In this paper, we introduce Channel-wise recurrent convolutional neural networks (RecNets), a family of novel, compact neural network architectures for computer vision tasks inspired by recurrent neural networks (RNNs). …

General Classificationimage-classificationImage Classification