%0 Generic %1 zhu2018heneta %A Zhu, Qiuyu %A Zhang, Ruixin %D 2018 %K CNN speedup %T HENet:A Highly Efficient Convolutional Neural Networks Optimized for Accuracy, Speed and Storage %U http://arxiv.org/abs/1803.02742 %X In order to enhance the real-time performance of convolutional neural networks(CNNs), more and more researchers are focusing on improving the efficiency of CNN. Based on the analysis of some CNN architectures, such as ResNet, DenseNet, ShuffleNet and so on, we combined their advantages and proposed a very efficient model called Highly Efficient Networks(HENet). The new architecture uses an unusual way to combine group convolution and channel shuffle which was mentioned in ShuffleNet. Inspired by ResNet and DenseNet, we also proposed a new way to use element-wise addition and concatenation connection with each block. In order to make greater use of feature maps, pooling operations are removed from HENet. The experiments show that our model's efficiency is more than 1 times higher than ShuffleNet on many open source datasets, such as CIFAR-10/100 and SVHN.

@misc{zhu2018heneta, abstract = {In order to enhance the real-time performance of convolutional neural networks(CNNs), more and more researchers are focusing on improving the efficiency of CNN. Based on the analysis of some CNN architectures, such as ResNet, DenseNet, ShuffleNet and so on, we combined their advantages and proposed a very efficient model called Highly Efficient Networks(HENet). The new architecture uses an unusual way to combine group convolution and channel shuffle which was mentioned in ShuffleNet. Inspired by ResNet and DenseNet, we also proposed a new way to use element-wise addition and concatenation connection with each block. In order to make greater use of feature maps, pooling operations are removed from HENet. The experiments show that our model's efficiency is more than 1 times higher than ShuffleNet on many open source datasets, such as CIFAR-10/100 and SVHN.}, added-at = {2018-03-08T07:58:50.000+0100}, author = {Zhu, Qiuyu and Zhang, Ruixin}, biburl = {https://www.bibsonomy.org/bibtex/241b8e58f6f510e9264e939c6ace1626c/jk_itwm}, description = {HENet:A Highly Efficient Convolutional Neural Networks Optimized for Accuracy, Speed and Storage}, interhash = {126863d0e02882da5f766e2a13896a4f}, intrahash = {41b8e58f6f510e9264e939c6ace1626c}, keywords = {CNN speedup}, note = {cite arxiv:1803.02742Comment: 11 pages,3 figures}, timestamp = {2018-03-08T07:58:50.000+0100}, title = {HENet:A Highly Efficient Convolutional Neural Networks Optimized for Accuracy, Speed and Storage}, url = {http://arxiv.org/abs/1803.02742}, year = 2018 }