Squeeze-and-Excitation Networks论文翻译

Squeeze-and-Excitation Networks

原文连接：

https://openaccess.thecvf.com/content_cvpr_2018/papers/Hu_Squeeze-and-Excitation_Networks_CVPR_2018_paper.pdf

GB/T 7714 Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.

MLA Hu, Jie, Li Shen, and Gang Sun. "Squeeze-and-excitation networks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.

APA Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7132-7141).

Abstract

Convolutional neural networks are built upon the convolution operation, which extracts informative features by fusing spatial and channel-wise information together within local receptive fields. In order to boost the representational power of a network, much existing work has shown the benefits of enhancing spatial encoding. In this work, we focus on channels and propose a novel architectural unit, which we term the “Squeeze-and-Excitation”(SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. We demonstrate that by stacking these blocks together, we can construct SENet architectures that generalise extremely well across challenging datasets. Crucially, we find that SE blocks produce significant performance improvements for existing state-of-the-art deep architectures at slight computational cost. SENets formed the foundation of our ILSVRC 2017 classification submission which won first place and significantly reduced the top-5 error to $2.251\%$ , achieving a $∼25\%$ relative improvement over the winning entry of 2016.

摘要

卷积神经网络建立在卷积运算的基础上，通过融合局部感受野内的空间信息和通道信息来提取信息特征。为了提高网络的表示能力，许多现有的工作已经显示出增强空间编码的好处。在这项工作中，我们专注于通道，并提出了一种新颖的架构单元，我们称之为“Squeeze-and-Excitation”（SE）块，通过显式地建模通道之间的相互依赖关系，自适应地重新校准通道式的特征响应。通过将这些块堆叠在一起，我们证明了我们可以构建SENet架构，在具有挑战性的数据集中可以进行泛化地非常好。关键的是，我们发现SE块以微小的计算成本为现有的最先进的深层架构产生了显著的性能改进。SENets是我们ILSVRC 2017分类提交的基础，它赢得了第一名，并将top-5错误率显著减少到 $2.251\%$ ，相对于2016年的获胜成绩取得了 $∼25\%$ 的相对改进。

1. Introduction

Convolutional neural networks (CNNs) have proven to be effective models for tackling a variety of visual tasks [19, 23, 29, 41]. For each convolutional layer, a set of filters are learned to express local spatial connectivity patterns along input channels. In other words, convolutional filters are expected to be informative combinations by fusing spatial and channel-wise information together, while restricted in local receptive fields. By stacking a series of convolutional layers interleaved with non-linearities and downsampling, CNNs are capable of capturing hierarchical patterns with global receptive fields as powerful image descriptions. Recent work has demonstrated the performance of networks can be improved by explicitly embedding learning mechanisms that help capture spatial correlations without requiring additional supervision. One such approach was popularised by the Inception architectures [14, 39], which showed that the network can achieve competitive accuracy by embedding multi-scale processes in its modules. More recent work has sought to better model spatial dependence [1, 27] and incorporate spatial attention [17].

1. 引言

卷积神经网络（CNNs）已被证明是解决各种视觉任务的有效模型[19,23,29,41]。对于每个卷积层，沿着输入通道学习一组滤波器来表达局部空间连接模式。换句话说，期望卷积滤波器通过融合空间信息和信道信息进行信息组合，而受限于局部感受野。通过叠加一系列非线性和下采样交织的卷积层，CNN能够捕获具有全局感受野的分层模式作为强大的图像描述。最近的工作已经证明，网络的性能可以通过显式地嵌入学习机制来改善，这种学习机制有助于捕捉空间相关性而不需要额外的监督。Inception架构推广了一种这样的方法[14,39]，这表明网络可以通过在其模块中嵌入多尺度处理来取得有竞争力的准确度。最近的工作在寻找更好地模型空间依赖[1,27]，结合空间注意力[17]。