A Lightweight Convolutional Neural Network with Hierarchical Multi-Scale Feature Fusion for Image Classification

Simple item page
dc.contributor.authorDembele, Adama
dc.contributor.authorMwangi, Ronald Waweru
dc.contributor.authorKube, Ananda Omutokoh
dc.date.accessioned2024-04-08T13:01:41Z
dc.date.available2024-04-08T13:01:41Z
dc.date.issued2024-02
dc.descriptionArticleen_US
dc.description.abstractConvolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.en_US
dc.identifier.citationDembele, A., Mwangi, R. W., & Kube, A. O. (2024). A Lightweight Convolutional Neural Network with Hierarchical Multi-Scale Feature Fusion for Image Classification. Journal of Computer and Communications, 12(2), 173-200.en_US
dc.identifier.urihttps://doi.org/10.4236/jcc.2024.122011
dc.identifier.urihttps://ir-library.ku.ac.ke/handle/123456789/27807
dc.language.isoenen_US
dc.publisherScientific Research Publishingen_US
dc.subjectMobileNeten_US
dc.subjectImage Classificationen_US
dc.subjectLightweight Convolutional Neural Networken_US
dc.subjectDepthwise Dilated Separable Convolutionen_US
dc.subjectHierarchical Multi-Scale Feature Fusionen_US
dc.titleA Lightweight Convolutional Neural Network with Hierarchical Multi-Scale Feature Fusion for Image Classificationen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
A Lightweight Convolutional Neural Network with....pdf
Size:
10.03 MB
Format:
Adobe Portable Document Format
Description:
Full text Research Article
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
RP-Department of Statistics and Actuarial Science