211 citations · 688 across the 13 of their papers we have counts for
Showing 2017Show all
3 papers · 1 filter
cs.CV2017★ 15 cited
EraseReLU: A Simple Way to Ease the Training of Deep Convolution Neural Networks
Xuanyi Dong, Guoliang Kang, Kun Zhan +1
For most state-of-the-art architectures, Rectified Linear Unit (ReLU) becomes a standard component accompanied with each layer. Although ReLU can ease the network training to an ex…
cs.CV2017★ 62 cited
PatchShuffle Regularization
Guoliang Kang, Xuanyi Dong, Liang Zheng +1
This paper focuses on regularizing the training of the convolutional neural network (CNN). We propose a new regularization approach named ``PatchShuffle`` that can be adopted in an…
cs.CV2017★ 37 cited
More is Less: A More Complicated Network with Less Inference Complexity
Xuanyi Dong, Junshi Huang, Yi Yang +1
In this paper, we present a novel and general network structure towards accelerating the inference process of convolutional neural networks, which is more complicated in network st…