Wang Wei, Zhang Yongde, Zhu Liqiang
Avic Xi'an Aircraft Industry Group Company Ltd., Xi'an, 710089 China.
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, 100044 China.
Cogn Neurodyn. 2023 Dec;17(6):1561-1573. doi: 10.1007/s11571-022-09913-z. Epub 2022 Nov 14.
Deep convolutional neural networks have achived remarkable progress on computer vision tasks over last years. These novel neural architecture are most designed manually by human experts, which is a time-consuming process and not the best solution. Hence neural architecture search (NAS) has become a hot research topic for the design of neural architecture. In this paper, we propose the dynamic receptive field (DRF) operation and measurable dense residual connections (DRC) in search space for designing efficient networks, i.e., DRENet. The search method can be deployed on the MobileNetV2-based search space. The experimental results on CIFAR10/100, SVHN, CUB-200-2011, ImageNet and COCO benchmark datasets and an application example in a railway intelligent surveillance system demonstrate the effectiveness of our scheme, which achieves superior performance.
近年来，深度卷积神经网络在计算机视觉任务上取得了显著进展。这些新颖的神经架构大多由人类专家手动设计，这是一个耗时的过程，并非最佳解决方案。因此，神经架构搜索（NAS）已成为神经架构设计的热门研究课题。在本文中，我们在搜索空间中提出了动态感受野（DRF）操作和可测量的密集残差连接（DRC），用于设计高效网络，即DRENet。该搜索方法可部署在基于MobileNetV2的搜索空间上。在CIFAR10/100、SVHN、CUB-200-2011、ImageNet和COCO基准数据集上的实验结果以及在铁路智能监控系统中的一个应用示例证明了我们方案的有效性，该方案取得了卓越的性能。
