SparseMaps: Convolutional networks with sparse feature maps for tiny image classification

作者：

Highlights：

• Imposing sparsity constraint on the activations along the depth of feature maps.

• Feature map dropout in the output of the last convolutional layer.

• The ensemble of multiple models obtained from the periodic learning rates.

摘要

•Imposing sparsity constraint on the activations along the depth of feature maps.•Feature map dropout in the output of the last convolutional layer.•The ensemble of multiple models obtained from the periodic learning rates.

论文关键词：Deep convolutional networks,Sparse feature map,DropMaps,Tiny image classification,Learning rate curve,Deep ensembles

论文评审过程：Received 4 June 2018, Revised 24 August 2018, Accepted 6 October 2018, Available online 19 October 2018, Version of Record 2 November 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.10.012