为目标检测提供无需重训练的实例级不确定性量化方法。
Instance-Level Post Hoc Uncertainty Quantification in Object Detection
- 提出MC-GLM方法，基于蒙特卡洛线性化模型实现快速实例级不确定性估计。
- 只需固定次数采样，可并行计算，效率高于需多次反向传播的方法。
- 在nuScenes数据集上验证，结果准确且适用于自动驾驶安全系统。
目标检测是自动驾驶中的关键安全部件，对边界框预测进行不确定性量化对于安全保障至关重要。无需重训练的后处理不确定性量化更符合实际部署需求，因此本文采用拉普拉斯近似。由于需要实例级不确定性，依赖多次反向传播的线性化方法效率低下，而采样方法并非完全后处理。为此，本文提出蒙特卡洛广义线性模型（MC-GLM），可在不依赖输出实例数量的前提下，以恒定采样次数实现近似后处理的实例级不确定性量化，并支持并行计算。在CenterPoint检测器与nuScenes数据集上的实验表明，该方法有效，生成的不确定性质量良好。
原文摘要 · Abstract (English)
Object detection is a safety-critical component of autonomous driving. It is essential to quantify the uncertainty in bounding-box predictions for safety assurance. Post hoc uncertainty quantification without retraining aligns with real-world deployment requirements; therefore, we employ the Laplace approximation. Because instance-level uncertainty is needed, linearized inference methods that require multiple backpropagations are not time-efficient, and sampling-based methods are not fully post hoc. We propose Monte-Carlo generalized linearized model (MC-GLM), which provides instance-level and approximately post hoc uncertainty quantification. The number of samples required in the Monte Carlo step is constant and independent of the number of output instances, so it can be parallelized. Experiments on the nuScenes dataset with the CenterPoint detector validate the effectiveness of our method, and the resulting uncertainties exhibit good quality.
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。