PydMobileNet: Improved Version of MobileNets with Pyramid Depthwise Separable Convolution
This work addresses the need for efficient convolutional neural networks for mobile and embedded vision applications, but it is incremental as it builds directly on the established MobileNet architecture.
The paper tackles the problem of reducing model size for real-time and mobile vision applications by proposing PydMobileNet, an improved version of MobileNets that uses pyramid depthwise separable convolution to capture more spatial information, achieving better performance on CIFAR-10 and CIFAR-100 benchmarks compared to MobileNet and other state-of-the-art networks.
Convolutional neural networks (CNNs) have shown remarkable performance in various computer vision tasks in recent years. However, the increasing model size has raised challenges in adopting them in real-time applications as well as mobile and embedded vision applications. Many works try to build networks as small as possible while still have acceptable performance. The state-of-the-art architecture is MobileNets. They use Depthwise Separable Convolution (DWConvolution) in place of standard Convolution to reduce the size of networks. This paper describes an improved version of MobileNet, called Pyramid Mobile Network. Instead of using just a $3\times 3$ kernel size for DWConvolution like in MobileNet, the proposed network uses a pyramid kernel size to capture more spatial information. The proposed architecture is evaluated on two highly competitive object recognition benchmark datasets (CIFAR-10, CIFAR-100). The experiments demonstrate that the proposed network achieves better performance compared with MobileNet as well as other state-of-the-art networks. Additionally, it is more flexible in fine-tuning the trade-off between accuracy, latency and model size than MobileNets.