Efficient data utilization is crucial for advancing 3D scene understanding in autonomous driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully …
Abstract 3D point-clouds and 2D images are different visual representations of the physical world. While human vision can understand both representations, computer vision models …
Recently, 3D object detection with sparse annotations has received great attention. However, current detectors usually perform poorly under very limited annotations. To …
CJ Ho, CH Tai, YY Lin, MH Yang… - Advances in Neural …, 2024 - proceedings.neurips.cc
Semi-supervised object detection is crucial for 3D scene understanding, efficiently addressing the limitation of acquiring large-scale 3D bounding box annotations. Existing …
Abstract State-of-the-art 3D object detectors are usually trained on large-scale datasets with high-quality 3D annotations. However, such 3D annotations are often expensive and time …
In this paper, we present a simple yet effective semi-supervised 3D object detector named DDS3D. Our main contributions have two-fold. On the one hand, different from previous …
Self-training is a well-established technique in semi-supervised learning, which leverages unlabeled data by generating pseudo-labels and incorporating them with a limited labeled …
H Wang, Z Zhang, J Gao, W Hu - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
This work proposes the first online asymmetric semi-supervised framework namely A- Teacher for LiDAR-based 3D object detection. Our motivation stems from the observation …
Current point-cloud detection methods have difficulty detecting the open-vocabulary objects in the real world, due to their limited generalization capability. Moreover, it is extremely …