Differentiable Convolution Search for Point Cloud Processing | |
Xing Nie2,3; Yongcheng Liu3; Shaohong Chen1; Jianlong Chang5; Chunlei Huo3; Gaofeng Meng2,3,4; Qi Tian5; Weiming Hu3; Chunhong Pan3 | |
2021-10 | |
会议日期 | 2021年10月10日至2021年10月17日 |
会议地点 | Montreal, Canada |
英文摘要 | 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 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/57519] ![]() |
专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
作者单位 | 1.Xidian University. 2.School of Artificial Intelligence, University of Chinese Academy of Sciences. 3.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences. 4.Centre for Artificial Intelligence and Robotics, HK Institute of Science & Innovation, CAS. 5.Huawei Cloud & AI. |
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]. 见:. Montreal, Canada. 2021年10月10日至2021年10月17日. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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