DSConvNet: A Lightweight Architecture for Extracting Image Features From Depthwise Separable Convolution Network for Edge Devices
Syed Muhammad Raza, Syed Murtaza Hussain Abidi, Md Masuduzzaman, Soo Young Shin · IEEE Access · 2025
This paper presents DSConvNet, a novel architecture based on depthwise separable convolutional blocks for efficient multi-class image classification. Despite progress in compact convolutional neural networks (CNNs), many existing models still impose high computational costs on resource‑constrained devices, limiting their real‑time applicability. To address this, DSConvNet employs four optimized DSConvNet blocks that reduce parameters, accelerate inference, and stabilize training. Each block combines a 2‑D convolution, depthwise convolution, batch normalization, and max‑pooling, forming an efficient yet expressive feature extractor. The resulting architecture achieves lower complexity, mitigates overfitting, and improves generalization. DSConvNet was evaluated on nine benchmark datasets GTSRB, BTSC, CIFAR‑10, CIFAR‑100, MNIST, Fashion‑MNIST, Imagewoof, Imagenette, and Caltech‑101 covering 100 object categories. Without GPU acceleration, the model attained 99.10% accuracy on GTSRB and 98.90% on BTSC, confirming its suitability for real‑time edge-based image classification under limited computational resources.