Boosting Object Detection Ensembles with Error Diversity
Boosting Object Detection Ensembles with Error Diversity
复制标题
DOI：
10.1109/icdm54844.2022.00105
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Ka-Ho Chow;Ling Liu
中科院分区：
文献类型：
--
作者：
Ka-Ho Chow;Ling Liu
物体检测在众多关键任务应用中发挥着关键作用。本文提出了一种称为 EDI 的焦点误差多样性框架，用于增强良性和对抗场景下目标检测集成的鲁棒性。我们引入了一种用于目标检测的集成修剪方法，使用一种新颖的焦点误差多样性度量作为鲁棒性协同指标。给定一个基本模型池，它会推荐具有较小整体尺寸的顶级子整体，但与使用所有可用的对象检测模型作为大型整体相比，仍可实现相同甚至更好的 mAP 性能。这是通过我们用于对象检测的负采样方法来捕获负相关程度和焦点误差多样性来测量集成中组件检测模型的故障独立性而实现的。对三个目标检测基准数据集的大量实验验证了 EDI 有效地选择了具有高 mAP 性能的时空高效的目标检测集合。
Object detection has played a pivotal role in numerous mission-critical applications. This paper presents a focal error diversity framework, called EDI, for strengthening the robustness of object detection ensembles under benign and adversarial scenarios. We introduce an ensemble pruning method for object detection using a novel focal error diversity measure as the robustness synergy indicator. Given a base model pool, it recommends top sub-ensembles with a smaller ensemble size yet achieving equivalent or even better mAP performance than using all available object detection models as a large ensemble. This is made possible by our negative sampling methods for object detection to capture the degree of negative correlations and the focal error diversity to measure the failure independence of component detection models in an ensemble. Extensive experiments on three object detection benchmark datasets validate that EDI effectively selects space-time efficient object detection ensembles with high mAP performance.