Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shifts

Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shifts

In image classification tasks, the evaluation of models' robustness to increased dataset shifts with a probabilistic framework is very well studied. However, object detection (OD) tasks pose other challenges for uncertainty estimation and evaluation.For example, one needs to evaluate both the quality of the label uncertainty (i.e., what?) and spatial uncertainty (i.e., where?) for a given bounding box, but that evaluation cannot be performed with more traditional average precision metrics (e.g., mAP). In this paper, we adapt the well-established YOLOv3 architecture to generate uncertainty estimations by introducing stochasticity in the form of Monte Carlo Dropout (MC-Drop), and evaluate it across different levels of dataset shift. We call this novel architecture Stochastic-YOLO, and provide an efficient implementation to effectively reduce the burden of the MC-Drop sampling mechanism at inference time. Finally, we provide some sensitivity analyses, while arguing that Stochastic-YOLO is a sound approach that improves different components of uncertainty estimations, in particular spatial uncertainties.

随机YOLO：数据集移位下的有效概率对象检测

在图像分类任务中，使用概率框架对模型对增加数据集移位的鲁棒性进行了很好的研究。但是，对象检测（OD）任务对不确定性估计和评估提出了其他挑战。.. 例如，对于给定的边界框，既需要评估标签不确定度（即，什么？）的质量，又需要评估空间不确定度（即，哪里？）的质量，但是该评估不能使用更传统的平均精度指标（例如，地图）。在本文中，我们通过引入蒙特卡洛·辍学（MC-Drop）形式的随机性，将完善的YOLOv3架构用于生成不确定性估计，并在不同级别的数据集移动中对其进行评估。我们将这种新颖的架构称为随机的YOLO，并提供了一种有效的实现方式，可以在推理时有效地减轻MC-Drop采样机制的负担。最后，我们提供了一些敏感性分析，同时认为随机（YOCH）方法可以改善不确定性估算的不同组成部分， （阅读更多）