Reliable Student: Addressing Noise in Semi-Supervised 3D Object Detection

arXiv:2404.17910v1 Announce Type: cross
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 …

3d object 3d object detection abstract arxiv benefit confidence cs.cv cs.lg data detection filtering however impact labeling labels noise object paper quality semi-supervised through training type