Adaptive Dilated Convolution For Human Pose Estimation | |
Zhengxiong Luo1,2,3,4![]() ![]() ![]() | |
2022-08 | |
会议名称 | International Conference on Pattern Recognition |
会议日期 | 2022-8 |
会议地点 | Montréal Québec |
摘要 | Most existing human pose estimation (HPE) methods exploit multi-scale information by fusing feature maps of four different spatial sizes, i.e. 1/4, 1/8, 1/16, and 1/32 of the input image. There are two drawbacks of this strategy: 1) feature maps of different spatial sizes may be not well spatially aligned, which potentially hurts the accuracy of keypoint location; 2) these scales are fixed and inflexible, which may restrict the generalization ability over various human sizes. To- wards these issues, we propose an adaptive dilated convolution (ADC). It can generate and fuse multi-scale features of the same spatial sizes by setting different dilation rates for different channels. Specifically, it uses a regression module to adaptively generate dilation rates for different channels. This also enables ADC to adjust the fused scales according to the sizes of test persons, and thus helps ADC to have better generalization ability. ADC can be end-to-end trained and easily plugged into existing methods. Extensive experiments show that ADC can bring consistent improvements to various HPE methods. The source codes will be released for further research. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/52066 |
专题 | 模式识别实验室 |
通讯作者 | Yan Huang |
作者单位 | 1.Megvii Inc 2.School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS) 3.Center for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition (NLPR) 4.Institute of Automation, Chinese Academy of Sciences (CASIA) |
第一作者单位 | 模式识别国家重点实验室; 中国科学院自动化研究所 |
通讯作者单位 | 模式识别国家重点实验室; 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhengxiong Luo,Zhicheng Wang,Yan Huang,et al. Adaptive Dilated Convolution For Human Pose Estimation[C],2022. |
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 | ||
bare_conf.pdf(579KB) | 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