Rethink ReLU to Training Better CNNs

TL;DR

This paper proposes a proportional module that adjusts the ratio of convolution to ReLU layers in CNNs, leading to improved generalization and performance across various architectures and benchmarks.

Contribution

It introduces a proportional module to optimize the convolution-to-ReLU ratio, enhancing CNN performance without extra computational cost.

Findings

Improved accuracy on multiple benchmarks

Better generalization ability in CNNs

Applicable to various network architectures

Abstract

Most of convolutional neural networks share the same characteristic: each convolutional layer is followed by a nonlinear activation layer where Rectified Linear Unit (ReLU) is the most widely used. In this paper, we argue that the designed structure with the equal ratio between these two layers may not be the best choice since it could result in the poor generalization ability. Thus, we try to investigate a more suitable method on using ReLU to explore the better network architectures. Specifically, we propose a proportional module to keep the ratio between convolution and ReLU amount to be N:M (N>M). The proportional module can be applied in almost all networks with no extra computational cost to improve the performance. Comprehensive experimental results indicate that the proposed method achieves better performance on different benchmarks with different network architectures, thus verify the superiority of our work.