计算机工程与应用 ›› 2020, Vol. 56 ›› Issue (18): 131-136.DOI: 10.3778/j.issn.1002-8331.1907-0024

• 模式识别与人工智能 • 上一篇    下一篇

轻量级目标识别深度神经网络及其应用

付佐毅,周世杰,李顶根   

  1. 1.华中科技大学 能源与动力工程学院,武汉 430074
    2.华中科技大学 中欧清洁与可再生能源学院,武汉 430074
  • 出版日期:2020-09-15 发布日期:2020-09-10

Lightweight Target Recognition Deep Neural Network and Its Application

FU Zuoyi, ZHOU Shijie, LI Dinggen   

  1. 1.School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
    2.China-EU Institute for Clean and Renewable Energy, Huazhong University of Science and Technology, Wuhan 430074, China
  • Online:2020-09-15 Published:2020-09-10

摘要:

针对当前一些主流的深度神经网络模型旨在追求准确率的提升,而忽略了模型的实时性及模型大小问题,提出了一种轻量级目标识别深度神经网络。基于深度分离卷积、分组卷积等轻量化的高效卷积方式,设计了用于图像特征提取的不变分辨率卷积模块和下采样模块,并依此构建了深度主干网络,并对网络进行了减枝。在创建的数据集上对视觉感知的目标识别模型进行了实验验证,获得了72.7%的mAP,在NVIDIA 1080Ti GPU上推理速度达到66.7 帧/s。

关键词: 目标识别, 轻量化, 剪枝

Abstract:

In view of the current mainstream deep neural network model, which aims to improve the accuracy and ignores the real-time performance and the size of the model, a lightweight target recognition deep neural network is proposed. Based on the high-efficiency convolution method such as depth separation convolution and packet convolution, an invariant resolution convolution module and a downsampling module for image feature extraction are designed. Based on this, a deep backbone network is constructed and the branch is reduced. The target recognition model of visual perception is experimentally verified on the dataset, and 72.7% of mAPs are obtained. The inference speed reaches 66.7 frames per second on the NVIDIA 1080Ti GPU.

Key words: target recognition, lightweight, pruning