Non-maximum suppression (NMS) is widely used in object detection pipelines for removing duplicated bounding boxes. The inconsistency between the confidence for NMS and the real localization confidence seriously affects detection performance. Prior works propose to predict Intersection-over-Union (IoU) between bounding boxes and corresponding ground-truths to improve NMS, while accurately predicting IoU is still a challenging problem. We argue that the complex definition of IoU and feature misalignment make it difficult to predict IoU accurately. In this paper, we propose a novel Decoupled IoU Regression (DIR) model to handle these problems. The proposed DIR decouples the traditional localization confidence metric IoU into two new metrics, Purity and Integrity. Purity reflects the proportion of the object area in the detected bounding box, and Integrity refers to the completeness of the detected object area. Separately predicting Purity and Integrity can divide the complex mapping between the bounding box and its IoU into two clearer mappings and model them independently. In addition, a simple but effective feature realignment approach is also introduced to make the IoU regressor work in a hindsight manner, which can make the target mapping more stable. The proposed DIR can be conveniently integrated with existing two-stage detectors and significantly improve their performance. Through a simple implementation of DIR with HTC, we obtain 51.3% AP on MS COCO benchmark, which outperforms previous methods and achieves state-of-the-art.
翻译:在物体探测管道中广泛使用非最大抑制(NMS)来清除重复的捆绑框。 NMS 的信任与实际本地化信任之间的不一致严重地影响了检测性能。 先前的工程提议预测捆绑框和相应的地面真相之间的交叉团结(IoU)来改进NMS, 而准确预测IoU仍然是一个具有挑战性的问题。 我们争辩说, IoU 的复杂定义和特征不匹配使得难以准确预测IoU。 在本文中,我们提议了一个新的Dcoupled IoU Regression (DIR) 模型来处理这些问题。 拟议的DoU 将传统的本地化信任(IoU) 拆分成两个新的尺寸, 纯度和完整性。 纯度反映了检测的捆绑框中目标区域的比例, 而完整性是指所探测到的COU区域的完整性。 单独预测纯度和完整性可以将IoU 和IoU IMU 的复杂映射分为两个更清晰的地图和模型。 此外, 一种简单但有效的地基调方法可以使以前的HoU 3 更精确的运行方式实现现有的方向。