Embracing Single Stride 3D Object Detector with Sparse Transformer | |
Fan L(范略)1,4,6,7![]() ![]() ![]() | |
2022-06 | |
会议名称 | 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
会议日期 | 2022/6/19-2022/6/24 |
会议地点 | 新奥尔良 |
摘要 | In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Over-looking this difference, many 3D detectors directly follow the common practice of 2D detectors, which downsample the feature maps even after quantizing the point clouds. In this paper, we start by rethinking how such multi-stride stereotype affects the LiDAR-based 3D object detectors. Our experiments point out that the downsampling operations bring few advantages, and lead to inevitable information loss. To remedy this issue, we propose Single-stride Sparse Transformer (SST) to maintain the original resolution from the beginning to the end of the network. Armed with transformers, our method addresses the problem of insufficient receptive field in single-stride architectures. It also cooperates well with the sparsity of point clouds and naturally avoids expensive computation. Eventually, our SST achieves state-of-the-art results on the large-scale Waymo Open Dataset. It is worth mentioning that our method can achieve exciting performance (83.8 LEVEL_1 AP on validation split) on small object (pedestrian) detection due to the characteristic of single stride. Our codes will be public soon. |
关键词 | 点云目标检测 自动驾驶 |
学科门类 | 工学::控制科学与工程 |
DOI | 10.1109/CVPR52688.2022.00827 |
URL | 查看原文 |
收录类别 | CPCI |
语种 | 英语 |
是否为代表性论文 | 是 |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
国重实验室规划方向分类 | 环境多维感知 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57417 |
专题 | 模式识别实验室 |
作者单位 | 1.中国科学院自动化所 2.伊利诺伊大学,香槟分校 3.卡耐基梅隆大学 4.中国科学院大学 5.清华大学 6.模式识别国家重点实验室 7.中国科学院大学未来技术学院 8.图森未来 9.中国科学院香港创新研究院,人工智能与机器人研究中心 |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Fan L,Pang ZQ,Zhang TY,et al. Embracing Single Stride 3D Object Detector with Sparse Transformer[C],2022. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Fan_Embracing_Single(1199KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论