Convolutional neural networks have spatial representations which read patterns in the vision tasks. Squeeze and excitation links the channel wise representations by explicitly modeling on channel level. Multi layer perceptrons learn global representations and in most of the models it is used often at the end after all convolutional layers to gather all the information learned before classification. We propose a method of inducing the global representations within channels to have better performance of the model. We propose SaEnet, Squeeze aggregated excitation network, for learning global channelwise representation in between layers. The proposed module takes advantage of passing important information after squeeze by having aggregated excitation before regaining its shape. We also introduce a new idea of having a multibranch linear(dense) layer in the network. This learns global representations from the condensed information which enhances the representational power of the network. The proposed module have undergone extensive experiments by using Imagenet and CIFAR100 datasets and compared with closely related architectures. The analyzes results that proposed models outputs are comparable and in some cases better than existing state of the art architectures.

翻译：卷积神经网络通过读取视觉任务中的模式来形成空间表示。挤压与激励通过在通道级别进行显式建模，将通道间的表示关联起来。多层感知机学习全局表示，在大多数模型中，它通常被用在所有卷积层之后，用于收集分类前学到的所有信息。我们提出了一种方法，通过在通道内引入全局表示来提升模型性能。我们提出了 SaEnet——挤压聚合激励网络，用于在层之间学习全局通道级表示。所提出的模块利用了在挤压后传递重要信息的优势，通过在恢复其形状之前进行聚合激励来实现。我们还引入了一个新概念，即在网络中使用多分支线性（全连接）层。该层从浓缩信息中学习全局表示，从而增强了网络的表示能力。所提出的模块在 ImageNet 和 CIFAR100 数据集上进行了大量实验，并与紧密相关的架构进行了比较。分析结果表明，所提出模型的输出与现有最先进架构相当，甚至在某些情况下更优。