15946

Weighted Residuals for Very Deep Networks

Falong Shen, Gang Zeng
Peking University
arXiv:1605.08831 [cs.CV], (28 May 2016)

@article{shen2016weighted,

   title={Weighted Residuals for Very Deep Networks},

   author={Shen, Falong and Zeng, Gang},

   year={2016},

   month={may},

   archivePrefix={"arXiv"},

   primaryClass={cs.CV}

}

Download Download (PDF)   View View   Source Source   

3101

views

Deep residual networks have recently shown appealing performance on many challenging computer vision tasks. However, the original residual structure still has some defects making it difficult to converge on very deep networks. In this paper, we introduce a weighted residual network to address the incompatibility between ReLU and element-wise addition and the deep network initialization problem. The weighted residual network is able to learn to combine residuals from different layers effectively and efficiently. The proposed models enjoy a consistent improvement over accuracy and convergence with increasing depths from 100+ layers to 1000+ layers. Besides, the weighted residual networks have little more computation and GPU memory burden than the original residual networks. The networks are optimized by projected stochastic gradient descent. Experiments on CIFAR-10 have shown that our algorithm has a faster convergence speed than the original residual networks and reaches a high accuracy at 95.3% with a 1192-layer model.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: