Asynchronous Event Processing with Local-Shift Graph Convolutional Network | |
Linhui Sun; Yifan Zhang; Jian Cheng; Hanqing Lu | |
2023-06 | |
会议日期 | 2023-2 |
会议地点 | WASHINGTON |
英文摘要 | Event cameras are bio-inspired sensors that produce sparse and asynchronous event streams instead of frame-based images at a high-rate. Recent works utilizing graph convolutional networks (GCNs) have achieved remarkable performance in recognition tasks, which model event stream as spatiotemporal graph. However, the computational mechanism of graph convolution introduces redundant computation when aggregating neighbors features, which limits the low latency nature of the events. And they perform a synchronous inference process, which can not achieve a fast response to the asynchronous event signals. This paper proposes a local-shift graph convolutional network (LSNet), which utilizes a novel local-shift operation equipped with a local spatiotemporal attention component to achieve efficient and adaptive aggregation of neighbors features. To improve the efficiency of pooling operation in feature extraction, we design a node-importance based parallel pooling method (NIPooling) for sparse and low-latency event data. Based on the calculated importance of each node, NIPooling can efficiently obtain uniform sampling results in parallel, which retains the diversity of event streams. Furthermore, for achieving a fast response to asynchronous event signals, an asynchronous event processing procedure is proposed to restrict the network nodes which need to recompute activations only to those affected by the new arrival event. Experimental results show that the computational cost can be reduced by nearly 9 times through using local-shift operation and the proposed asynchronous procedure can further improve the inference efficiency, while achieving state-of-the-art performance on gesture recognition and object recognition. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/54540] |
专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 |
通讯作者 | Yifan Zhang |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Linhui Sun,Yifan Zhang,Jian Cheng,et al. Asynchronous Event Processing with Local-Shift Graph Convolutional Network[C]. 见:. WASHINGTON. 2023-2. |
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