论文标题
对象检测作为概率集预测
Object Detection as Probabilistic Set Prediction
论文作者
论文摘要
准确的不确定性估计对于在安全关键系统中部署深层对象探测器至关重要。概率对象探测器的开发和评估受到现有绩效指标的缺点的阻碍，这些绩效指标往往涉及任意阈值或限制检测器的分布选择。在这项工作中，我们建议将对象检测视为一个设定的预测任务，其中检测器预测对象集的分布。使用负对数可能性的有限有限集，我们提出了一个适当的评分规则，用于评估和训练概率对象探测器。所提出的方法可以应用于现有的概率检测器，没有阈值，并可以在体系结构之间进行公平的比较。在可可数据集上评估了三种不同类型的检测器。我们的结果表明，现有检测器的培训已针对非稳定指标进行了优化。我们希望鼓励开发新的对象探测器，以准确估计自己的不确定性。可在https://github.com/georghess/pmb-nll上获得代码。
Accurate uncertainty estimates are essential for deploying deep object detectors in safety-critical systems. The development and evaluation of probabilistic object detectors have been hindered by shortcomings in existing performance measures, which tend to involve arbitrary thresholds or limit the detector's choice of distributions. In this work, we propose to view object detection as a set prediction task where detectors predict the distribution over the set of objects. Using the negative log-likelihood for random finite sets, we present a proper scoring rule for evaluating and training probabilistic object detectors. The proposed method can be applied to existing probabilistic detectors, is free from thresholds, and enables fair comparison between architectures. Three different types of detectors are evaluated on the COCO dataset. Our results indicate that the training of existing detectors is optimized toward non-probabilistic metrics. We hope to encourage the development of new object detectors that can accurately estimate their own uncertainty. Code available at https://github.com/georghess/pmb-nll.
