Label-Efficient 3D Object Detection For Road-Side Units
Minh-Quan Dao (Institut National de Recherche en Informatique et en Automatique (INRIA))
Holger Caesar (TU Delft - Intelligent Vehicles)
Julie Stephany Berrio (Australian Centre for Robotics)
Mao Shan (Australian Centre for Robotics)
Stewart Worrall (Australian Centre for Robotics)
Vincent Frémont (Ecole Centrale Nantes)
Ezio Malis (Institut National de Recherche en Informatique et en Automatique (INRIA))
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Occlusion presents a significant challenge for safety-critical applications such as autonomous driving. Collaborative perception has recently attracted a large research interest thanks to the ability to enhance the perception of autonomous vehicles via deep information fusion with intelligent roadside units (RSU), thus minimizing the impact of occlusion. While significant advancement has been made, the data-hungry nature of these methods creates a major hurdle for their realworld deployment, particularly due to the need for annotated RSU data. Manually annotating the vast amount of RSU data required for training is prohibitively expensive, given the sheer number of intersections and the effort involved in annotating point clouds. We address this challenge by devising a label-efficient object detection method for RSU based on unsupervised object discovery. Our paper introduces two new modules: one for object discovery based on a spatial temporal aggregation of point clouds, and another for refinement. Furthermore, we demonstrate that fine-tuning on a small portion of annotated data allows our object discovery models to narrow the performance gap with, or even surpass, fully supervised models.