Depthwise Separable Convolutions with Deep Residual Convolutions

TL;DR

This study proposes an optimized Xception architecture tailored for edge devices, aiming for lightweight and efficient deployment, and incorporates the depthwise separable convolutions with deep residual convolutions of the Xception architecture to develop a small and efficient model for edge devices.

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.

Figures (6)

• Figure 1: Proposed Architecture. the data first goes through the entry flow, then through the middle flow-1 which is repeated 4 times, then through the middle flow-2, and finally through the exit flow. Note that all Convolution and SeparableConvolution layers are followed by batch normalization (not included in the diagram). All SeparableConvolution layers use a depth multiplier of 1 (no depth expansion).
• Figure 2: (a): Comparison of training time among XceptionNet, optimized XceptionNet, and optimized XceptionNet with data. (b): Comparison of training loss among XceptionNet, optimized XceptionNet, and optimized XceptionNet with data.
• Figure 3: Comparison of memory usage among XceptionNet, optimized XceptionNet, and optimized XceptionNet with data
• Figure 4: Comparison of validation accuracy among XceptionNet, optimized XceptionNet, and optimized XceptionNet with data
• Figure 5: Comparison of validation loss among XceptionNet, optimized XceptionNet, and optimized XceptionNet with data