Global-connected network with generalized ReLU activation

作者：

Highlights：

• This work presents a novel deep-connected architecture of CNN with detailed analytical analysis and extensive experiments on several datasets.

• A new activation function is presented to approximate arbitrary complex functions with analytical analysis on both forward pass and backward pass.

• The experiments show the competitive performance of our designed network with less parameters and shallower architecture, compared with other state-of-art models.

摘要

•This work presents a novel deep-connected architecture of CNN with detailed analytical analysis and extensive experiments on several datasets.•A new activation function is presented to approximate arbitrary complex functions with analytical analysis on both forward pass and backward pass.•The experiments show the competitive performance of our designed network with less parameters and shallower architecture, compared with other state-of-art models.

论文关键词：CNN,Computer vision,Deep learning,Activation

论文评审过程：Received 9 November 2018, Revised 9 June 2019, Accepted 8 July 2019, Available online 9 July 2019, Version of Record 15 July 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.07.006