Localization Quality Estimation (LQE) is crucial and popular in the recent advancement of dense object detectors since it can provide accurate ranking scores that benefit the Non-Maximum Suppression processing and improve detection performance. As a common practice, most existing methods predict LQE scores through vanilla convolutional features shared with object classification or bounding box regression. In this paper, we explore a completely novel and different perspective to perform LQE -- based on the learned distributions of the four parameters of the bounding box. The bounding box distributions are inspired and introduced as "General Distribution" in GFLV1, which describes the uncertainty of the predicted bounding boxes well. Such a property makes the distribution statistics of a bounding box highly correlated to its real localization quality. Specifically, a bounding box distribution with a sharp peak usually corresponds to high localization quality, and vice versa. By leveraging the close correlation between distribution statistics and the real localization quality, we develop a considerably lightweight Distribution-Guided Quality Predictor (DGQP) for reliable LQE based on GFLV1, thus producing GFLV2. To our best knowledge, it is the first attempt in object detection to use a highly relevant, statistical representation to facilitate LQE. Extensive experiments demonstrate the effectiveness of our method. Notably, GFLV2 (ResNet-101) achieves 46.2 AP at 14.6 FPS, surpassing the previous state-of-the-art ATSS baseline (43.6 AP at 14.6 FPS) by absolute 2.6 AP on COCO {\tt test-dev}, without sacrificing the efficiency both in training and inference. Code will be available at https://github.com/implus/GFocalV2.
翻译:46. 本地化质量估计(LQE)对于最近密集天体探测器的进步至关重要,也很受欢迎,因为它能够提供准确的排名分数,有利于非最高限值处理和改进检测性能。作为常见做法,大多数现有方法通过与目标分类或捆绑框回归共享的香草卷变相特征预测LQE分数。在本文件中,我们探索了一个全新的和不同的视角来实施LQE -- -- 其依据是捆绑框的四个参数的学术分布。捆绑箱的分发被启发并被引入为GFLV1中的“通用分布”,它描述了预测的捆绑盒的不确定性。这种属性使得一个捆绑盒的分发统计数据与其真实的本地化质量密切相关。具体地说,一个最高峰的捆绑盒分布通常与高的本地化质量相对反。通过利用分发统计数据与实际本地化质量之间的密切关联,我们开发了一个相当轻的分发-Guid质量预测(DGQQQP),用于基于GFLV1的可靠 LQE, 绝对值显示预测性包装箱的不确定性的不确定性。因此,在GFLVS-V2 测试中使用了我们之前的测试方法。