Query2Uncertainty：分布偏移下3D目标检测的鲁棒不确定性量化与校准
Query2Uncertainty: Robust Uncertainty Quantification and Calibration for 3D Object Detection under Distribution Shift
对做3D检测部署的人，这篇给出一个可复用的后处理校准思路：直接拿DETR式检测器的潜变量object query特征拟合密度估计器，用密度值在分布偏移下同时重校准分类置信度与边界框回归不确定性，无需重训练检测器。
原文依据 couples post-hoc calibrators with the feature density of latent object queries from DETR-style 3D object detectors
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论面向3D目标检测的可靠不确定性估计对于部署安全自主系统至关重要，然而现代检测器仍校准不佳，在分布偏移下尤为明显。尽管事后校准方法能够缓解该问题并在分布内测试中提供更好的校准，但它们在分布偏移场景下无法自适应。本文针对该问题，提出一种密度感知校准方法，将事后校准器与DETR式3D目标检测器中潜变量object query的特征密度相耦合。这些query构成紧凑的、位置与类别感知的特征，非常适合密度估计，使我们的方法能够在分布偏移场景下调整模型置信度。通过在这些query特征上拟合密度估计器，我们的方法联合重校准分类不确定性与边界框回归不确定性。在多视角相机检测器和基于LiDAR的检测器上，我们的方法在分布内与分布偏移场景下均持续优于标准事后方法。代码：https://tillbeemelmanns.github.io/query2uncertainty
英文原文摘要 1134 字符
Reliable uncertainty estimation for 3D object detection is critical for deploying safe autonomous systems, yet modern detectors remain poorly calibrated, especially under distribution shifts. Although post-hoc calibration methods address this issue and provide improved calibration for in-distribution tests, they fail to adapt in distribution-shifted scenarios. In this work, we address this issue and introduce a density-aware calibration method that couples post-hoc calibrators with the feature density of latent object queries from DETR-style 3D object detectors. These queries form a compact, location and class-aware feature, ideal for density estimation, allowing our approach to adjust model confidences in distribution-shift scenarios. By fitting a density estimator on these query features, our approach jointly recalibrates both classification and bounding box regression uncertainties. On both a multi-view camera and LiDAR-based detector, our approach consistently outperforms standard post-hoc methods in both in-distribution and distribution-shifted scenarios. Code: https://tillbeemelmanns.github.io/query2uncertainty