Deep Networks with Stochastic Depth

Abstract

Very deep convolutional networks with hundreds of layers have led to significant reductions in error on competitive benchmarks. Although the unmatched expressiveness of the many layers can be highly desirable at test time, training very deep networks comes with its own set of challenges. The gradients can vanish, the forward flow often diminishes, and the training time can be painfully slow. To address these problems, we propose stochastic depth, a training procedure that enables the seemingly contradictory setup to train short networks and use deep networks at test time. We start with very deep networks but during training, for each mini-batch, randomly drop a subset of layers and bypass them with the identity function. This simple approach complements the recent success of residual networks. It reduces training time substantially and improves the test error significantly on almost all data sets that we used for evaluation. With stochastic depth we can increase the depth of residual networks even beyond 1200 layers and still yield meaningful improvements in test error (4.91% on CIFAR-10).

DOI: 10.1007/978-3-319-46493-0_39

Extracted Key Phrases

9 Figures and Tables

05010015020162017
Citations per Year

171 Citations

Semantic Scholar estimates that this publication has 171 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Huang2016DeepNW, title={Deep Networks with Stochastic Depth}, author={Gao Huang and Yu Sun and Zhuang Liu and Daniel Sedra and Kilian Q. Weinberger}, booktitle={ECCV}, year={2016} }