Depthwise Separable Convolutions with Deep Residual Convolutions
This work addresses the problem of deploying efficient deep learning models on resource-constrained edge devices, though it is incremental as it builds on existing Xception architecture.
The authors tackled the high computational cost of the Xception architecture for object detection on edge devices by proposing an optimized version using depthwise separable convolutions with deep residual convolutions, resulting in reduced parameters, memory usage, and computational load while outperforming Xception on CIFAR-10.
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.