Max-Pooling Dropout for Regularization of Convolutional Neural Networks
Abstract
Recently, dropout has seen increasing use in deep learning. For deep convolutional neural networks, dropout is known to work well in fully-connected layers. However, its effect in pooling layers is still not clear. This paper demonstrates that max-pooling dropout is equivalent to randomly picking activation based on a multinomial distribution at training time. In light of this insight, we advocate employing our proposed probabilistic weighted pooling, instead of commonly used max-pooling, to act as model averaging at test time. Empirical evidence validates the superiority of probabilistic weighted pooling. We also compare max-pooling dropout and stochastic pooling, both of which introduce stochasticity based on multinomial distributions at pooling stage.
Keywords
Cite
@article{arxiv.1512.01400,
title = {Max-Pooling Dropout for Regularization of Convolutional Neural Networks},
author = {Haibing Wu and Xiaodong Gu},
journal= {arXiv preprint arXiv:1512.01400},
year = {2015}
}
Comments
The journal version of this paper [arXiv:1512.00242] has been published in Neural Networks, http://www.sciencedirect.com/science/article/pii/S0893608015001446