The deployment of deep neural networks in safety-critical systems necessitates reliable and efficient uncertainty quantification (UQ). A practical and widespread strategy for UQ is repurposing stochastic regularizers as scalable approximate Bayesian inference methods, such as Monte Carlo Dropout (MCD) and MC-DropBlock (MCDB). However, this paradigm remains under-explored for Stochastic Depth (SD), a regularizer integral to the residual-based backbones of most modern architectures. While prior work demonstrated its empirical promise for segmentation, a formal theoretical connection to Bayesian variational inference and a benchmark on complex, multi-task problems like object detection are missing. In this paper, we first provide theoretical insights connecting Monte Carlo Stochastic Depth (MCSD) to principled approximate variational inference. We then present the first comprehensive empirical benchmark of MCSD against MCD and MCDB on state-of-the-art detectors (YOLO, RT-DETR) using the COCO and COCO-O datasets. Our results position MCSD as a robust and computationally efficient method that achieves highly competitive predictive accuracy (mAP), notably yielding slight improvements in calibration (ECE) and uncertainty ranking (AUARC) compared to MCD. We thus establish MCSD as a theoretically-grounded and empirically-validated tool for efficient Bayesian approximation in modern deep learning.

翻译：深度神经网络在安全关键系统中的部署需要可靠且高效的不确定性量化（UQ）。一种实用且广泛采用的UQ策略是将随机正则化器重新用作可扩展的近似贝叶斯推断方法，例如蒙特卡洛Dropout（MCD）和MC-DropBlock（MCDB）。然而，这种范式对于随机深度（SD）——一种嵌入大多数现代架构中基于残差的主干网络的正则化器——仍未得到充分探索。尽管先前的工作在分割任务中展示了其经验潜力，但缺乏与贝叶斯变分推断的正式理论联系，以及在复杂多任务问题（如目标检测）上的基准测试。在本文中，我们首先提供理论见解，将蒙特卡洛随机深度（MCSD）与原则性的近似变分推断联系起来。随后，我们在最先进的检测器（YOLO、RT-DETR）上，使用COCO和COCO-O数据集，首次展示了MCSD与MCD及MCDB的全面经验基准测试。我们的结果将MCSD定位为一种鲁棒且计算高效的方法，它实现了极具竞争力的预测精度（mAP），尤其在校准（ECE）和不确定性排名（AUARC）方面相比MCD略有改进。因此，我们将MCSD确立为一种理论上有依据且经验上经过验证的工具，用于现代深度学习中的高效贝叶斯近似。