Squeeze aggregated excitation network

TL;DR

This paper introduces SaEnet, a novel neural network architecture that enhances global channel-wise representations within layers using aggregated excitation and multi-branch dense layers, leading to improved performance.

Contribution

The paper proposes SaEnet, a new method for integrating global channel-wise representations within CNN layers using aggregated excitation and multi-branch dense layers.

Findings

SaEnet achieves comparable or better accuracy than state-of-the-art models.

Extensive experiments on ImageNet and CIFAR100 validate the effectiveness.

The multi-branch dense layer enhances the network's representational power.

Abstract

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.