Convolutional neural networks (CNNs) have been successfully applied in a range of fields such as image classification and object segmentation. To improve their expressivity, various techniques, such as novel CNN architectures, have been explored. However, the performance gain from such techniques tends to diminish. To address this challenge, many researchers have shifted their focus to increasing the non-linearity of neurons, the fundamental building blocks of neural networks, to enhance the network expressivity. Nevertheless, most of these approaches incur a large number of parameters and thus formidable computation cost inevitably, impairing their efficiency to be deployed in practice. In this work, an efficient quadratic neuron structure is proposed to preserve the non-linearity with only negligible parameter and computation cost overhead. The proposed quadratic neuron can maximize the utilization of second-order computation information to improve the network performance. The experimental results have demonstrated that the proposed quadratic neuron can achieve a higher accuracy and a better computation efficiency in classification tasks compared with both linear neurons and non-linear neurons from previous works.

翻译：卷积神经网络（CNNs）已成功应用于图像分类、目标分割等多个领域。为提升其表达能力，研究者探索了多种技术（如新型CNN架构），但此类技术带来的性能增益趋于衰减。针对这一挑战，许多研究者转而聚焦于增强神经元（神经网络的基本构建模块）的非线性以提升网络表达能力。然而，现有方法大多引入大量参数，导致计算成本急剧上升，严重影响了其实际部署效率。本文提出一种高效的二次神经元结构，能在仅增加微量参数和计算开销的前提下保持非线性。该二次神经元通过最大化利用二阶计算信息来提升网络性能。实验结果表明，在分类任务中，本文提出的二次神经元相较于现有工作中的线性神经元和非线性神经元，均能实现更高的准确率和更优的计算效率。