With the development of deep learning technologies, object detection algorithms have made significant progress in terms of detection speed and detection performance. However, the detection speed of current detection networks still does not meet the requirements of real-world applications in some scenarios. In this paper, we propose a faster non-maximum suppression (FNMS) algorithm that reduces the processing time by a large margin while achieving the same detection precision compared with the traditional non-maximum suppression (NMS) algorithm. Moreover, an attempt is made to adopt additional lightweight network structures to improve the speed of the detection network. By combining our FNMS algorithm with other network optimization strategies, we are able to improve the detection speed of YOLO v3 on the DOTA dataset by 165%.

中文翻译：

---

目标检测网络的通用优化策略

随着深度学习技术的发展，目标检测算法在检测速度和检测性能方面都取得了长足的进步。然而，当前检测网络的检测速度在某些场景下仍然不能满足实际应用的要求。在本文中，我们提出了一种更快的非极大值抑制（FNMS）算法，与传统的非极大值抑制（NMS）算法相比，该算法在实现相同检测精度的同时大大减少了处理时间。此外，尝试采用额外的轻量级网络结构来提高检测网络的速度。通过将我们的 FNMS 算法与其他网络优化策略相结合，我们能够将 YOLO v3 在 DOTA 数据集上的检测速度提高 165%。