The superior performance of object detectors is often established under the condition that the test samples are in the same distribution as the training data. However, in many practical applications, out-of-distribution (OOD) instances are inevitable and usually lead to uncertainty in the results. In this paper, we propose a novel, intuitive, and scalable probabilistic object detection method for OOD detection. Unlike other uncertainty-modeling methods that either require huge computational costs to infer the weight distributions or rely on model training through synthetic outlier data, our method is able to distinguish between in-distribution (ID) data and OOD data via weight parameter sampling from proposed Gaussian distributions based on pre-trained networks. We demonstrate that our Bayesian object detector can achieve satisfactory OOD identification performance by reducing the FPR95 score by up to 8.19% and increasing the AUROC score by up to 13.94% when trained on BDD100k and VOC datasets as the ID datasets and evaluated on COCO2017 dataset as the OOD dataset.

翻译：目标检测器的卓越性能通常建立在测试样本与训练数据同分布的假设之上。然而在实际应用中，分布外（OOD）样本不可避免，且往往导致检测结果存在不确定性。本文提出一种新颖、直观且可扩展的概率性目标检测方法用于OOD检测。与其它需要巨大计算成本推断权重分布或依赖合成异常数据训练模型的不确定性建模方法不同，本方法通过基于预训练网络的权重参数采样（服从高斯分布），能够有效区分分布内（ID）数据与OOD数据。实验表明，当以BDD100k和VOC数据集作为ID数据集进行训练，并以COCO2017数据集作为OOD数据集进行评估时，我们的贝叶斯目标检测器可将FPR95分数降低最多8.19%，同时将AUROC分数提升最多13.94%，实现令人满意的OOD识别性能。