Efficient Attention Mechanism for Dynamic Convolution in Lightweight Neural Network

Abstract

Light-weight convolutional neural networks (CNNs) suffer limited feature representation capabilities due to low computational budgets, resulting in degradation in performance. To make CNNs more efficient, dynamic neural networks (DyNet) have been proposed to increase the complexity of the model by using the Squeeze-and-Excitation (SE) module to adaptively obtain the importance of each convolution kernel through the attention mechanism. However, the attention mechanism in the SE network (SENet) selects all channel information for calculations, which brings essential challenges: (a) interference caused by the internal redundant information; and (b) increasing number of network calculations. To address the above problems, this work proposes a dynamic convolutional network (termed as EAM-DyNet) to reduce the number of channels in feature maps by extracting only the useful spatial information. EAM-DyNet first uses the random channel reduction and channel grouping reduction methods to remove the redundancy in the information. As the downsampling of information can lead to the loss of useful information, it then applies an adaptive average pooling method to maintain the information integrity. Extensive experimental results on the baseline demonstrate that EAM-DyNet outperformed the existing approaches, thus it can achieve higher accuracy of the network test and less network parameters.

Ultimate pose estimation: A comparative study

“…MuPoTS‐3D is a collection of 3D human pose data for testing and evaluating the performance of multi‐person pose estimation algorithms. It contains a variety of poses, including standing, walking, sitting, and lying down (Bouazizi et al, 2022; Ding, 2023). It includes both static and dynamic poses, with multiple people in each scene.…”

Image-Based Malware Classification Using VGG19 Network and Spatial Convolutional Attention

“…Dynamic spatial convolution uses a global average pooling mechanism which is easy to understand since in any given image all the areas are not equally important. Some specific regions are better suited for the task and are more useful [63].…”