论文标题
伪螺旋罗：在自主驾驶系统中，用于半监督对象检测的可靠伪标签生成
PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems
论文作者
论文摘要
半监督对象检测方法被广泛用于自主驾驶系统中，其中只有一小部分对象被标记。为了将标记对象的信息传播到未标记的对象，必须生成用于未标记对象的伪标记。尽管已证明伪标记可以显着提高半监视对象检测的性能，但基于图像的方法在视频帧中的应用导致使用此类伪标记的伪造导致许多错过或虚假检测。在本文中，我们提出了一种新方法伪螺旋桨，以利用视频帧中的运动连续性来生成稳健的伪标记。具体而言，伪螺旋桨使用一种新型的双向伪标签传播方法来补偿误导。基于功能的融合技术也用于抑制推理噪声。大规模CityScapes数据集的广泛实验表明，我们的方法在MAP75上的最先进的半监督对象检测方法优于最先进的半监督对象检测方法。
Semi-supervised object detection methods are widely used in autonomous driving systems, where only a fraction of objects are labeled. To propagate information from the labeled objects to the unlabeled ones, pseudo-labels for unlabeled objects must be generated. Although pseudo-labels have proven to improve the performance of semi-supervised object detection significantly, the applications of image-based methods to video frames result in numerous miss or false detections using such generated pseudo-labels. In this paper, we propose a new approach, PseudoProp, to generate robust pseudo-labels by leveraging motion continuity in video frames. Specifically, PseudoProp uses a novel bidirectional pseudo-label propagation approach to compensate for misdetection. A feature-based fusion technique is also used to suppress inference noise. Extensive experiments on the large-scale Cityscapes dataset demonstrate that our method outperforms the state-of-the-art semi-supervised object detection methods by 7.4% on mAP75.
