IEEE Trans Pattern Anal Mach Intell. 2016 Apr;38(4):814-30. doi: 10.1109/TPAMI.2015.2465908.
Current top performing object detectors employ detection proposals to guide the search for objects, thereby avoiding exhaustive sliding window search across images. Despite the popularity and widespread use of detection proposals, it is unclear which trade-offs are made when using them during object detection. We provide an in-depth analysis of twelve proposal methods along with four baselines regarding proposal repeatability, ground truth annotation recall on PASCAL, ImageNet, and MS COCO, and their impact on DPM, R-CNN, and Fast R-CNN detection performance. Our analysis shows that for object detection improving proposal localisation accuracy is as important as improving recall. We introduce a novel metric, the average recall (AR), which rewards both high recall and good localisation and correlates surprisingly well with detection performance. Our findings show common strengths and weaknesses of existing methods, and provide insights and metrics for selecting and tuning proposal methods.
当前表现最佳的目标检测算法使用检测提议来引导对目标的搜索，从而避免在图像上进行全面的滑动窗口搜索。尽管检测提议已经非常流行并被广泛应用，但是在使用它们进行目标检测时，其具体的权衡取舍仍然不明确。我们深入分析了 12 种提议方法以及 4 种基准方法，涉及提议的可重复性、在 PASCAL、ImageNet 和 MS COCO 数据集上的真实标注召回率，以及它们对 DPM、R-CNN 和 Fast R-CNN 检测性能的影响。我们的分析表明，对于目标检测，提高提议的定位准确性与提高召回率同样重要。我们引入了一个新的度量标准——平均召回率（AR），它既奖励高召回率，又奖励良好的定位，与检测性能的相关性出人意料地好。我们的研究结果展示了现有方法的常见优缺点，并提供了用于选择和调整提议方法的思路和指标。
