Robustly and accurately localizing objects in real-world environments can be challenging due to noisy data, hardware limitations, and the inherent randomness of physical systems. To account for these factors, existing works estimate the aleatoric uncertainty of object detectors by modeling their localization output as a Gaussian distribution $\mathcal{N}(\mu,\,\sigma^{2})\,$, and training with loss attenuation. We identify three aspects that are unaddressed in the state of the art, but warrant further exploration: (1) the efficient and mathematically sound propagation of $\mathcal{N}(\mu,\,\sigma^{2})\,$ through non-linear post-processing, (2) the calibration of the predicted uncertainty, and (3) its interpretation. We overcome these limitations by: (1) implementing loss attenuation in EfficientDet, and proposing two deterministic methods for the exact and fast propagation of the output distribution, (2) demonstrating on the KITTI and BDD100K datasets that the predicted uncertainty is miscalibrated, and adapting two calibration methods to the localization task, and (3) investigating the correlation between aleatoric uncertainty and task-relevant error sources. Our contributions are: (1) up to five times faster propagation while increasing localization performance by up to 1\%, (2) up to fifteen times smaller expected calibration error, and (3) the predicted uncertainty is found to correlate with occlusion, object distance, detection accuracy, and image quality.

翻译：在现实环境中稳健且精确地定位物体可能具有挑战性，其原因包括噪声数据、硬件限制以及物理系统的固有随机性。为应对这些因素，现有研究通过将物体检测器的定位输出建模为高斯分布 $\mathcal{N}(\mu,\,\sigma^{2})\,$ 并采用损失衰减进行训练，来估计其偶然不确定性。我们识别出当前技术现状中未被充分处理但值得深入探索的三个问题：(1) $\mathcal{N}(\mu,\,\sigma^{2})\,$ 通过非线性后处理时的高效且数学严谨的传播，(2) 预测不确定性的校准，以及 (3) 其可解释性。我们通过以下方式克服这些局限：(1) 在EfficientDet中实现损失衰减，并提出两种确定性方法用于输出分布的精确且快速传播，(2) 在KITTI和BDD100K数据集上证明预测不确定性存在校准偏差，并将两种校准方法适配到定位任务中，(3) 研究偶然不确定性与任务相关误差源之间的相关性。我们的贡献包括：(1) 传播速度提升高达五倍，同时定位性能提升最高1%，(2) 预期校准误差缩小高达十五倍，以及 (3) 发现预测不确定性与遮挡、物体距离、检测精度和图像质量相关。