Differentiable Convolution Search for Point Cloud Processing
Xing Nie1,2; Yongcheng Liu1; Shaohong Chen4; Jianlong Chang3; Chunlei Huo1; Gaofeng Meng1,2,5; Qi Tian3; Weiming Hu1; Chunhong Pan1
2021-10
会议名称IEEE/CVF International Conference on Computer Vision (ICCV)
会议日期2021年10月10日至2021年10月17日
会议地点Montreal, Canada
摘要

Exploiting convolutional neural networks for point cloud  processing is quite challenging, due to the inherent irregular  distribution and discrete shape representation of point  clouds.  To address these problems, many handcrafted convolution  variants have sprung up in recent years.  Though  with elaborate design, these variants could be far from optimal  in sufficiently capturing diverse shapes formed by discrete  points.  In this paper, we propose PointSeaConv, i.e.,  a novel differential convolution search paradigm on point  clouds.  It can work in a purely data-driven manner and  thus is capable of auto-creating a group of suitable convolutions  for geometric shape modeling.  We also propose  a joint optimization framework for simultaneous search of  internal convolution and external architecture, and introduce  epsilon-greedy algorithm to alleviate the effect of discretization  error.  As a result, PointSeaNet, a deep network  that is sufficient to capture geometric shapes at both convolution  level and architecture level, can be searched out  for point cloud processing.  Extensive experiments strongly  evidence that our proposed PointSeaNet surpasses current  handcrafted deep models on challenging benchmarks  across multiple tasks with remarkable margins.

语种英语
七大方向——子方向分类三维视觉
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
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/57519
专题多模态人工智能系统全国重点实验室_先进时空数据分析与学习
作者单位1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences.
2.School of Artificial Intelligence, University of Chinese Academy of Sciences.
3.Huawei Cloud & AI.
4.Xidian University.
5.Centre for Artificial Intelligence and Robotics, HK Institute of Science & Innovation, CAS.
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
Xing Nie,Yongcheng Liu,Shaohong Chen,et al. Differentiable Convolution Search for Point Cloud Processing[C],2021.
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
Differentiable Convo(1249KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Xing Nie]的文章
[Yongcheng Liu]的文章
[Shaohong Chen]的文章
百度学术
百度学术中相似的文章
[Xing Nie]的文章
[Yongcheng Liu]的文章
[Shaohong Chen]的文章
必应学术
必应学术中相似的文章
[Xing Nie]的文章
[Yongcheng Liu]的文章
[Shaohong Chen]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Differentiable Convolution Search for Point Cloud Processing.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。