Knowledge Commons of Institute of Automation,CAS
Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition | |
Ke Cheng1,2; Yifan Zhang1,2; Congqi Cao4; Lei Shi1,2; Jian Cheng1,2,3; Hanqing Lu1,2 | |
2020-08 | |
会议名称 | European Conference on Computer Vision (ECCV) |
会议日期 | 2020-8 |
会议地点 | 线上 |
摘要 | In skeleton-based action recognition, graph convolutional networks (GCNs) have achieved remarkable success. Nevertheless, how to efficiently model the spatial-temporal skeleton graph without introducing extra computation burden is a challenging problem for industrial deployment. In this paper, we rethink the spatial aggregation in existing GCN-based skeleton action recognition methods and discover that they are limited by coupling aggregation mechanism. Inspired by the decoupling aggregation mechanism in CNNs, we propose decoupling GCN to boost the graph modeling ability with no extra computation, no extra latency, no extra GPU memory cost, and less than 10\% extra parameters. Another prevalent problem of GCNs is over-fitting. Although dropout is a widely used regularization technique, it is not effective for GCNs, due to the fact that activation units are correlated between neighbor nodes. We propose DropGraph to discard features in correlated nodes, which is particularly effective on GCNs. Moreover, we introduce an attention-guided drop mechanism to enhance the regularization effect. All our contributions introduce zero extra computation burden at deployment. We conduct experiments on three datasets (NTU-RGBD, NTU-RGBD-120, and Northwestern-UCLA) and exceed the state-of-the-art performance with less computation cost. |
关键词 | skeleton-based action recognition, decoupling GCN, DropGraph |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48924 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
通讯作者 | Yifan Zhang |
作者单位 | 1.NLPR & AIRIA, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.CAS Center for Excellence in Brain Science and Intelligence Technology 4.School of Computer Science, Northwestern Polytechnical University |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Ke Cheng,Yifan Zhang,Congqi Cao,et al. Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition[C],2020. |
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 | ||
ECCV2020__Decoupling(2350KB) | 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