.png){kind=icon}
返回
Mutual information-driven self-supervised point cloud pre-training
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2024.112741.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Learning universal representations from unlabeled 3D point clouds is essential to improve the generalization and safety of autonomous driving. Generative self-supervised point cloud pre-training with low-level features as pretext tasks is a mainstream paradigm. However, from the perspective of mutual information, this approach is constrained by spatial information and entangled representations. In this study, we propose a generalized generative self-supervised point cloud pre-training framework called GPICTURE. High-level features were used as an additional pretext task to enhance the understanding of semantic information. Considering the varying difficulties caused by the discrimination of voxel features, we designed inter-class and intra-class discrimination-guided masking (I2Mask) to set the masking ratio adaptively. Furthermore, to ensure a hierarchical and stable reconstruction process, centered kernel alignment-guided hierarchical reconstruction and differential-gated progressive learning were employed to control multiple reconstruction tasks. Complete theoretical analyses demonstrated that high-level features can enhance the mutual information between latent features and high-level features, as well as the input point cloud. On Waymo, nuScenes, and SemanticKITTI, we achieved a 75.55% mAP for 3D object detection, 79.7% mIoU for 3D semantic segmentation, and 18.8% mIoU for occupancy prediction. Specifically, with only 50% of the fine-tuning data required, the performance of GPICURE was close to that of training from scratch with 100% of the fine-tuning data. In addition, consistent visualization with downstream tasks and a 57% reduction in weight disparity demonstrated a better fine-tuning starting point. The project page is hosted at https://gpicture-page.github.io/.
Keyword:
Self-supervised learning
Autonomous driving
Point cloud scene understanding
Mutual information
High-level features
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
5.2W
机构
引用论文
.png){kind=icon}
FlowFormer: 3D scene flow estimation for point clouds with transformersFlowFormer: 使用transformers进行点云的3D场景流估计
PREAI
分享收藏Prediction of the driver's focus of attention based on feature visualization of a deep autonomous driving model基于深度自动驾驶模型特征可视化的驾驶员注意力集中预测
PREAI
分享收藏Health Literacy – a review of research using the European Health Literacy Questionnaire (HLS-EU-Q16) in 2010-2018健康素养-2010-2018使用欧洲健康素养问卷 (HLS-EU-Q16) 进行的研究综述
OAAI
OAAI分享收藏PV-RCNN plus plus : Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object DetectionPv-rcnn plus: 具有局部向量表示的点体素特征集抽象，用于3D对象检测OAAI
OAAI分享收藏
查看更多内容