目标检测中基于采样的不确定性技术的融合策略评估
Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detection
摘要：
最近出现了一种基于采样的技术，用于估计深度神经网络中的认知不确定性。虽然这些方法可以通过简单地平均样本来应用于分类或语义分割任务，但对于目标检测来说情况并非如此，其中检测样本边界框必须准确地关联和合并。弱合并策略会显著降低检测器的性能，并产生不可靠的不确定性度量。本文首次深入研究了不同的联想策略和合并策略的效果。我们比较不同的组合，三个空间和两个语义的亲和力措施与四个聚类方法的MC辍学与Single Shot多盒检测器。实验结果表明，正确选择仿射-聚类组合可以大大提高分类和空间不确定性估计的有效性，从而提高目标检测性能。我们的评估基于一个新的混合数据集，模拟近开集条件（语义相似的未知类），远开集条件（语义不同的未知类）和常见的闭集条件（只有已知类）。
英文摘要：
There has been a recent emergence of sampling-based techniques for estimating epistemic uncertainty in deep neural networks. While these methods can be applied to classification or semantic segmentation tasks by simply averaging samples, this is not the case for object detection, where detection sample bounding boxes must be accurately associated and merged. A weak merging strategy can significantly degrade the performance of the detector and yield an unreliable uncertainty measure. This paper provides the first in-depth investigation of the effect of different association and merging strategies. We compare different combinations of three spatial and two semantic affinity measures with four clustering methods for MC Dropout with a Single Shot Multi-Box Detector. Our results show that the correct choice of affinity-clustering combination can greatly improve the effectiveness of the classification and spatial uncertainty estimation and the resulting object detection performance. We base our evaluation on a new mix of datasets that emulate near open-set conditions (semantically similar unknown classes), distant open-set conditions (semantically dissimilar unknown classes) and the common closed-set conditions (only known classes).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
