.png){kind=icon}
返回
GAL: Graph-Induced Adaptive Learning for Weakly Supervised 3D Object Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/TITS.2023.3265387.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Weakly Supervised 3D Object Detection (WS3DOD) aims to perform 3D object detection with little reliance on 3D labels, which greatly reduces the cost of 3D annotations. In recent literature, the pseudo-label-based approach brings impressive performance, which generates 3D pseudo-labels from 2D bounding boxes. Despite their success, two key issues remain unresolved that reduce the quality of 3D pseudo-labels: 1) the existing local object locating algorithm can not capture complete clusters of points globally, and 2) the existing algorithm can not capture sparse points caused by the unevenly distributed points obtained by LiDAR cameras. Hence, we propose GAL, a Graph-induced Adaptive Learning algorithm, to generate 3D pseudo-labels. First, we propose the Cluster Locating algorithm based on the Minimum Spanning Tree (MST) to globally locate the objects, which can leverage the characteristic that points inside an object are compact while points between objects are discrete. Second, we propose a density-guided adaptive learning algorithm to optimise the Cluster Locating algorithm, named Cuboid Drift. Cuboid Drift considers the inhomogeneous distribution of reflected points on different reflective surfaces of LiDAR imaging. Finally, 3D pseudo-labels generated by GAL are leveraged to train 3D detectors. Extensive experiments on the challenging KITTI and DAIR-V2X-V dataset demonstrate that GAL without 3D labels can be comparable with strongly supervised approaches and outperforms the previous state-of-the-art WS3DOD methods. Moreover, our method saves 88% of the time spent on pseudo-label generation.
Keyword:
Three-dimensional displays
Point cloud compression
Clustering algorithms
Object detection
Annotations
Laser radar
Adaptive learning
3D object detection
weakly supervised learning
multimodal alignment
minimum spanning tree
期刊
IF:
8.4
论文数:
9.7K
被引数:
6.3W
机构
引用论文
.png){kind=icon}
Maximizing the Computational Efficiency of Temporary Housing Decision Support Following Disasters
PREAI
分享收藏
分享收藏分享收藏
查看更多内容