Depthwise Separable Convolutions with Deep Residual Convolutions

TL;DR

This paper introduces an optimized Xception architecture that combines depthwise separable convolutions with deep residual convolutions, significantly reducing computational cost and improving efficiency for edge device deployment in object detection tasks.

Contribution

It proposes a novel lightweight Xception-based model integrating depthwise separable and residual convolutions for efficient edge computing applications.

Findings

Reduces model parameters and memory usage

Requires less training time than original Xception

Outperforms original Xception in accuracy on CIFAR-10

Abstract

The recent advancement of edge computing enables researchers to optimize various deep learning architectures to employ them in edge devices. In this study, we aim to optimize Xception architecture which is one of the most popular deep learning algorithms for computer vision applications. The Xception architecture is highly effective for object detection tasks. However, it comes with a significant computational cost. The computational complexity of Xception sometimes hinders its deployment on resource-constrained edge devices. To address this, we propose an optimized Xception architecture tailored for edge devices, aiming for lightweight and efficient deployment. We incorporate the depthwise separable convolutions with deep residual convolutions of the Xception architecture to develop a small and efficient model for edge devices. The resultant architecture reduces parameters, memory usage, and computational load. The proposed architecture is evaluated on the CIFAR 10 object detection dataset. The evaluation result of our experiment also shows the proposed architecture is smaller in parameter size and requires less training time while outperforming Xception architecture performance.