工作高效的并行非极大值抑制核
Work-Efficient Parallel Non-Maximum Suppression Kernels
AI总结：
本文提出一种面向嵌入式GPU架构的高度可扩展并行非极大值抑制（NMS）算法，可处理数千个同时检测，在Tegra X1/X2上每帧约1ms完成聚类，比需学习CNN的先进方法快14至40倍。
摘要：
在目标检测的背景下，滑动窗口分类器和单次卷积神经网络（CNN）元架构通常会在特定对象的真实位置周围产生多个具有相似高分且重叠的候选窗口。非极大值抑制（NMS）是在该检测簇中选择单个代表性候选的过程，以便为给定图片中出现的每个对象获得唯一的检测结果。在本文中，我们提出了一种用于嵌入式GPU架构的高度可扩展的NMS算法，该算法从头开始设计，以处理在给定图片上具有数千个同时检测的工作负载。我们的核函数可直接应用于其他顺序NMS算法，如FeatureNMS、Soft-NMS或AdaptiveNMS，这些算法共享经典贪婪NMS方法的内部工作原理。获得的性能结果表明，我们的并行NMS算法能够在NVIDIA Tegra X1和NVIDIA Tegra X2片上GPU上以大约1 ms的时间对每帧1024个同时检测到的对象进行聚类，而在NVIDIA Tegra K1上耗时2 ms。此外，与需要从标注数据中学习CNN的最先进NMS方法相比，我们提出的并行贪婪NMS算法实现了14倍至40倍的加速。
英文摘要：
In the context of object detection, sliding-window classifiers and single-shot Convolutional Neural Network (CNN) meta-architectures typically yield multiple overlapping candidate windows with similar high scores around the true location of a particular object. Non-Maximum Suppression (NMS) is the process of selecting a single representative candidate within this cluster of detections, so as to obtain a unique detection per object appearing on a given picture. In this paper, we present a highly scalable NMS algorithm for embedded GPU architectures that is designed from scratch to handle workloads featuring thousands of simultaneous detections on a given picture. Our kernels are directly applicable to other sequential NMS algorithms such as FeatureNMS, Soft-NMS or AdaptiveNMS that share the inner workings of the classic greedy NMS method. The obtained performance results show that our parallel NMS algorithm is capable of clustering 1024 simultaneous detected objects per frame in roughly 1 ms on both NVIDIA Tegra X1 and NVIDIA Tegra X2 on-die GPUs, while taking 2 ms on NVIDIA Tegra K1. Furthermore, our proposed parallel greedy NMS algorithm yields a 14x-40x speed up when compared to state-of-the-art NMS methods that require learning a CNN from annotated data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
