Abstract
Semi-supervised 3D object detection can benefit from the promising pseudo-labeling technique when labeled data is limited. However, recent approaches have overlooked the impact of noisy pseudo-labels during training, despite efforts to enhance pseudo-label quality through confidence-based filtering. In this paper, we examine the impact of noisy pseudo-labels on IoU-based target assignment and propose the Reliable Student framework, which incorporates two complementary approaches to mitigate errors. First, it involves a class-aware target assignment strategy that reduces false negative assignments in difficult classes. Second, it includes a reliability weighting strategy that suppresses false positive assignment errors while also addressing remaining false negatives from the first step. The reliability weights are determined by querying the teacher network for confidence scores of the student-generated proposals. Our work surpasses the previous state-of-the-art on KITTI 3D object detection benchmark on point clouds in the semi-supervised setting. On 1% labeled data, our approach achieves a 6.2% AP improvement for the pedestrian class, despite having only 37 labeled samples available. The improvements become significant for the 2% setting, achieving 6.0% AP and 5.7% AP improvements for the pedestrian and cyclist classes, respectively.
Abstract (translated)
在标签数据有限的情况下,半监督的3D物体检测可以通过有前景的伪标签技术受益。然而,最近的尝试忽略了在训练过程中噪音伪标签的影响,尽管通过基于信心的过滤来增强伪标签质量的尝试。在本文中,我们研究了噪音伪标签对IoU基于目标分配的影响,并提出了可信赖学生框架,该框架包含两种互补方法来减轻错误。首先,它涉及一个类感知的目标分配策略,可以减少难以分类类别的错误否定分配。其次,它包括一个可靠性加权策略,可以在抑制错误 positive assignment error的同时解决第一步骤中的剩余错误 false negatives。可靠性权重是由查询学生生成的建议的网络的置信度分数来确定的。我们在半监督设置的KITTI 3D物体检测基准点云上超越了以前的最先进水平。在仅1%标记数据的条件下,我们的方法实现了行人类的AP改进率6.2%,而只有37个标记样本可用。这种改进在2%设置中变得显著,分别实现了行人类和自行车类的AP改进率6.0%和5.7%。
URL
https://arxiv.org/abs/2404.17910
