Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation
2022
会议录名称PROCEEDINGS OF THE IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION
ISSN1063-6919
卷号2022-June
页码8469-8478
发表状态已发表
DOI10.1109/CVPR52688.2022.00829
摘要This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation. Directly employing previous distillation approaches yields inferior results due to the intrinsic challenges of point cloud, i.e., sparsity, randomness and varying density. To tackle the aforementioned problems, we propose the Point-to-Voxel Knowledge Distillation (PVD), which transfers the hidden knowledge from both point level and voxel level. Specifically, we first leverage both the pointwise and voxelwise output distillation to complement the sparse supervision signals. Then, to better exploit the structural information, we divide the whole point cloud into several supervoxels and design a difficulty-aware sampling strategy to more frequently sample supervoxels containing less-frequent classes and faraway objects. On these supervoxels, we propose inter-point and inter-voxel affinity distillation, where the similarity information between points and voxels can help the student model better capture the structural information of the surrounding environment. We conduct extensive experiments on two popular LiDAR segmentation benchmarks, i.e., nuScenes [3] and SemanticKITTI [1]. On both benchmarks, our PVD-consistently outperforms previous distillation approaches by a large margin on three representative backbones, i.e., Cylinder3D [36], [37], SPVNAS [25] and MinkowskiNet [5]. Notably, on the challenging nuScenes and SemanticKITTI datasets, our method can achieve roughly 75% MACs reduction and 2× speedup on the competitive Cylinder3D model and rank 1st on the SemanticKITTI leaderboard among all published algorithms11https://competitions.codalab.org/competitions/20331#results (single-scan competition) till 2021-11-18 04:00 Pacific Time, and our method is termed Point-Voxel-KD. Our method (PV-KD) ranks 3rd on the multi-scan challenge till 2021-12-1 00:00 Pacific Time. Our code is available at https://github.com/cardwing/Codes-for-PVKD. © 2022 IEEE.
会议名称2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
出版地10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA
会议地点New Orleans, LA, United states
会议日期June 19, 2022 - June 24, 2022
URL查看原文
收录类别EI ; CPCI-S
语种英语
WOS研究方向Computer Science ; Imaging Science & Photographic Technology
WOS类目Computer Science, Artificial Intelligence ; Imaging Science & Photographic Technology
WOS记录号WOS:000870759101051
出版者IEEE Computer Society
EI入藏号20224613120193
原始文献类型Conference article (CA)
来源库IEEE
引用统计
正在获取...
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/248931
专题信息科学与技术学院_PI研究组_马月昕
通讯作者Hou, Yuenan
作者单位
1.Shanghai AI Lab, Shanghai, Peoples R China
2.Chinese Univ Hong Kong, Hong Kong, Peoples R China
3.ShanghaiTech Univ, Shanghai, Peoples R China
4.Nanyang Technol Univ, S Lab, Singapore, Singapore
推荐引用方式
GB/T 7714
Hou, Yuenan,Zhu, Xinge,Ma, Yuexin,et al. Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation[C]. 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA:IEEE Computer Society,2022:8469-8478.
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
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Hou, Yuenan]的文章
[Zhu, Xinge]的文章
[Ma, Yuexin]的文章
百度学术
百度学术中相似的文章
[Hou, Yuenan]的文章
[Zhu, Xinge]的文章
[Ma, Yuexin]的文章
必应学术
必应学术中相似的文章
[Hou, Yuenan]的文章
[Zhu, Xinge]的文章
[Ma, Yuexin]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 10.1109@CVPR52688.2022.00829.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。