为行人检测设计更精准的评估体系，提升安全关键性能比较
Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection
- 基于图像分割划分8类错误，实现细粒度误差分析
- 在CityPersons-reasonable上取得无额外训练数据的最新最优表现
- 适合关注自动驾驶安全性和模型真实性能的开发者
可靠的行人检测是自动驾驶系统的关键步骤。然而，当前性能评估基准存在缺陷：用于验证数据集不同子集的指标导致对深度神经网络行人检测器的真实性能评估不准确。由于图像分割能提供街景的细粒度信息，可作为起点自动区分检测过程中的各类错误。本文提出8种行人检测错误类别，并设计新指标用于在此基础上进行性能对比。我们使用这些新指标评估简化版APD的多种主干网络，展示了在安全关键性能方面更精细、更稳健的模型比较方式。仅用简单架构即在CityPersons-reasonable上达到无需额外训练数据的最先进水平。
原文摘要 · Abstract (English)
Reliable pedestrian detection represents a crucial step towards automated driving systems. However, the current performance benchmarks exhibit weaknesses. The currently applied metrics for various subsets of a validation dataset prohibit a realistic performance evaluation of a DNN for pedestrian detection. As image segmentation supplies fine-grained information about a street scene, it can serve as a starting point to automatically distinguish between different types of errors during the evaluation of a pedestrian detector. In this work, eight different error categories for pedestrian detection are proposed and new metrics are proposed for performance comparison along these error categories. We use the new metrics to compare various backbones for a simplified version of the APD, and show a more fine-grained and robust way to compare models with each other especially in terms of safety-critical performance. We achieve SOTA on CityPersons-reasonable (without extra training data) by using a rather simple architecture.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。