[论文解读] HybridNets: End-to-End Perception Network

Dat Vu, Bao Ngo+1 more|arXiv (Cornell University)|Mar 17, 2022

Advanced Neural Network Applications被引用 68

一句话总结

HybridNets 提供一个端到端的多任务感知网络，用于交通对象检测、可行驶区域分割和车道检测，具有优化的头部网络、自适应锚点和均衡的训练策略，达到较高准确度和实时性能。

ABSTRACT

End-to-end Network has become increasingly important in multi-tasking. One prominent example of this is the growing significance of a driving perception system in autonomous driving. This paper systematically studies an end-to-end perception network for multi-tasking and proposes several key optimizations to improve accuracy. First, the paper proposes efficient segmentation head and box/class prediction networks based on weighted bidirectional feature network. Second, the paper proposes automatically customized anchor for each level in the weighted bidirectional feature network. Third, the paper proposes an efficient training loss function and training strategy to balance and optimize network. Based on these optimizations, we have developed an end-to-end perception network to perform multi-tasking, including traffic object detection, drivable area segmentation and lane detection simultaneously, called HybridNets, which achieves better accuracy than prior art. In particular, HybridNets achieves 77.3 mean Average Precision on Berkeley DeepDrive Dataset, outperforms lane detection with 31.6 mean Intersection Over Union with 12.83 million parameters and 15.6 billion floating-point operations. In addition, it can perform visual perception tasks in real-time and thus is a practical and accurate solution to the multi-tasking problem. Code is available at https://github.com/datvuthanh/HybridNets.

研究动机与目标

• 研究用于驾驶场景的端到端多任务感知网络。
• 提出基于加权双向特征网络的高效分割头部和框/类别预测网络。
• 引入在加权双向特征网络的每个层级自动定制的锚点。
• 开发高效的训练损失与策略，以平衡多任务优化。
• 展示在交通对象检测、可行驶区域分割和车道检测上的多任务性能。

提出的方法

• 基于加权双向特征网络构建的高效分割头和框/类别预测网络。
• 在加权双向特征网络的每个层级自动定制锚点。
• 一种优化的训练损失函数和策略，以平衡跨任务的学习。
• 端到端框架，支持同时进行交通对象检测、可行驶区域分割和车道检测。
• 在 Berkeley DeepDrive Dataset 上的评估，与现有方法比较。

实验结果

研究问题

• RQ1 与现有方法相比，端到端多任务感知网络是否能在检测、可行驶区域分割和车道检测上提升准确性？
• RQ2 带有定制锚点的加权双向特征网络是否能提升各任务的性能和效率？
• RQ3 所提出的训练策略在平衡多任务优化和实现实时推断方面有多有效？

主要发现

• HybridNets 在 Berkeley DeepDrive Dataset 上达到 77.3 的 mean Average Precision。
• 车道检测达到 31.6 的 mean Intersection over Union。
• 该模型使用 12.83 百万参数和 15.6 十亿 FLOPs。
• 该方法实现实时运行，使其在多任务驾驶感知中具有实用性。
• HybridNets 的代码可在所提供的 URL 获取。