[论文解读] Real-time object detection method based on improved YOLOv4-tiny

Zicong Jiang, Liquan Zhao+2 more|arXiv (Cornell University)|Nov 9, 2020

Advanced Neural Network Applications参考文献 28被引用 174

一句话总结

本文提出一种通过改进 YOLOv4-tiny、用修改后的骨干网络（以 ResBlock-D 替代两个 CSPBlock）以及辅助残差网络实现更丰富的特征提取，从而在更高速度下保持与 YOLOv4-tiny 相当的精度的实时对象检测方法。

ABSTRACT

The "You only look once v4"(YOLOv4) is one type of object detection methods in deep learning. YOLOv4-tiny is proposed based on YOLOv4 to simple the network structure and reduce parameters, which makes it be suitable for developing on the mobile and embedded devices. To improve the real-time of object detection, a fast object detection method is proposed based on YOLOv4-tiny. It firstly uses two ResBlock-D modules in ResNet-D network instead of two CSPBlock modules in Yolov4-tiny, which reduces the computation complexity. Secondly, it designs an auxiliary residual network block to extract more feature information of object to reduce detection error. In the design of auxiliary network, two consecutive 3x3 convolutions are used to obtain 5x5 receptive fields to extract global features, and channel attention and spatial attention are also used to extract more effective information. In the end, it merges the auxiliary network and backbone network to construct the whole network structure of improved YOLOv4-tiny. Simulation results show that the proposed method has faster object detection than YOLOv4-tiny and YOLOv3-tiny, and almost the same mean value of average precision as the YOLOv4-tiny. It is more suitable for real-time object detection.

研究动机与目标

• 通过在简化网络的同时保持精度，推动在移动和嵌入式设备上的实时目标检测。
• 通过对骨干网络的架构改动来降低计算量。
• 通过辅助残差网络和注意力机制提升特征提取以降低检测误差。

提出的方法

• 将 YOLOv4-tiny 中的两个 CSPBlock 模块替换为两个 ResBlock-D 模块，以降低计算量。
• 引入一个辅助残差网络模块以提取更多的对象特征信息。
• 在辅助网络中，使用两个连续的 3x3 卷积以创建 5x5 的感受野以获取全局特征。
• 应用通道注意力和空间注意力以增强有信息的特征。
• 将辅助网络与骨干网络合并，形成最终改进的 YOLOv4-tiny 架构。

实验结果

研究问题

• RQ1 在不牺牲检测精度的前提下，是否可以简化 YOLOv4-tiny 的骨干网络？
• RQ2 辅助残差网络是否改善了对小物体和大物体的特征表示？
• RQ3 注意力机制和更大的感受野是否在实时检测器中降低检测错误？

主要发现

• 所提出的方法比 YOLOv4-tiny 和 YOLOv3-tiny 运行得更快。
• 该方法的平均精度均值（mAP）几乎与 YOLOv4-tiny 相当。
• 改进后的架构更适合在移动和嵌入式设备上进行实时对象检测。