论文标题
基于哈希的非最大抑制作用用于拥挤的对象检测
Hashing-based Non-Maximum Suppression for Crowded Object Detection
论文作者
论文摘要
在本文中，我们提出了一种算法，该算法为基于哈希的非最大抑制（HNMS），以有效抑制非最大最大框以进行对象检测。非最大最大抑制（NMS）是抑制与形状相似的紧密位置的框的必不可少的组件。当盒子数量大，尤其是对于拥挤的场景时，时间成本趋于巨大。 HNM的基本思想是首先将每个框映射到离散的代码（哈希单元），然后在同一单元格中删除以较低的信心删除框。考虑到跨工会（IOU）的交叉路口为公制，我们提出了一种简单而有效的哈希算法，名为iouhash，该算法保证了同一单元内的盒子在同一单元中的盒子足够接近iOU绑定的较低。对于两个阶段探测器，我们用HNM替换了区域提案网络中的NMS，并以可比的精度观察到显着的加速。对于一个阶段探测器，HNMs用作前过滤器，以较大的边缘加速抑制。在Carpk，Sku-1110k，CrowdHuman数据集上进行了广泛的实验，以证明HNM的效率和有效性。代码以\ url {https://github.com/microsoft/hnms.git}发布。
In this paper, we propose an algorithm, named hashing-based non-maximum suppression (HNMS) to efficiently suppress the non-maximum boxes for object detection. Non-maximum suppression (NMS) is an essential component to suppress the boxes at closely located locations with similar shapes. The time cost tends to be huge when the number of boxes becomes large, especially for crowded scenes. The basic idea of HNMS is to firstly map each box to a discrete code (hash cell) and then remove the boxes with lower confidences if they are in the same cell. Considering the intersection-over-union (IoU) as the metric, we propose a simple yet effective hashing algorithm, named IoUHash, which guarantees that the boxes within the same cell are close enough by a lower IoU bound. For two-stage detectors, we replace NMS in region proposal network with HNMS, and observe significant speed-up with comparable accuracy. For one-stage detectors, HNMS is used as a pre-filter to speed up the suppression with a large margin. Extensive experiments are conducted on CARPK, SKU-110K, CrowdHuman datasets to demonstrate the efficiency and effectiveness of HNMS. Code is released at \url{https://github.com/microsoft/hnms.git}.
