VeloxNet: Efficient Spatial Gating for Lightweight Embedded Image Classification

2026-03-19

AI Summary

This work proposes VeloxNet, a lightweight convolutional neural network architecture tailored for embedded image classification, where balancing accuracy and resource constraints is critical. VeloxNet introduces spatial gating units (SGUs) into embedded vision for the first time, replacing the Fire modules in SqueezeNet with gMLP blocks to model global spatial dependencies within a single layer—thereby overcoming the limited receptive fields of conventional local convolutions. By integrating efficient depthwise convolutions with multilayer perceptron structures, VeloxNet achieves notable performance gains: it improves weighted F1 scores by 6.32%, 30.83%, and 2.51% on the AIDER, CDD, and LDD datasets, respectively, while reducing the parameter count by 46.1% compared to SqueezeNet.

Technology Category

• Computer Vision: Large Vision Models
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Deploying deep learning models on embedded devices for tasks such as aerial disaster monitoring and infrastructure inspection requires architectures that balance accuracy with strict constraints on model size, memory, and latency. This paper introduces VeloxNet, a lightweight CNN architecture that replaces SqueezeNet's fire modules with gated multi-layer perceptron (gMLP) blocks for embedded image classification. Each gMLP block uses a spatial gating unit (SGU) that applies learned spatial projections and multiplicative gating, enabling the network to capture spatial dependencies across the full feature map in a single layer. Unlike fire modules, which are limited to local receptive fields defined by small convolutional kernels, the SGU provides global spatial modeling at each layer with fewer parameters. We evaluate VeloxNet on three aerial image datasets: the Aerial Image Database for Emergency Response (AIDER), the Comprehensive Disaster Dataset (CDD), and the Levee Defect Dataset (LDD), comparing against eleven baselines including MobileNet variants, ShuffleNet, EfficientNet, and recent vision transformers. VeloxNet reduces the parameter count by 46.1% relative to SqueezeNet (from 740,970 to 399,366) while improving weighted F1 scores by 6.32% on AIDER, 30.83% on CDD, and 2.51% on LDD. These results demonstrate that substituting local convolutional modules with spatial gating blocks can improve both classification accuracy and parameter efficiency for resource-constrained deployment. The source code will be made publicly available upon acceptance of the paper.

Problem

• embedded image classification
• model efficiency
• aerial image analysis
• resource-constrained deployment
• lightweight neural networks

Innovation

• spatial gating unit
• gMLP
• lightweight CNN
• global spatial modeling
• embedded image classification