.png){kind=icon}
返回
Unbiased feature position alignment for human pose estimation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2023.03.063.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Multi-scale feature fusion is a commonly-used module in existing deep-learning models, and feature misalignment occurs in the process of feature fusion. The spatial misalignment hinders the learning of semantic representation with multi-scale levels, but which has not received much attention. This misalignment problem is caused by the feature position shift after using the convolution and interpolation operation in feature fusion. To solve the misalignment problem, this paper formulates the shift error mathematically and proposes a plug-and-play unbiased feature position alignment strategy to align convolution with interpolation. As a model-agnostic approach, unbiased feature position alignment can boost the performance of different models without introducing extra parameters. Furthermore, the unbiased feature position alignment is applied to build an unbiased human pose estimation method. Experimental results have demonstrated the effectiveness of the proposed unbiased pose model in comparison to the state-of-the-arts, especially in the low-resolution field. The codes are shared at https:// github.com/WangChen100/Unbiased-Feature-Position-Alignment-for-Human-Pose-Estimation.(c) 2023 Elsevier B.V. All rights reserved.
Keyword:
Multi -scale fusion
Position misalignment
Unbiased feature position alignment
Unbiased human pose model
Human pose estimation
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Electrochemically assisted micro localized grafting of aptamers in a microchannel engraved in fluorinated thermoplastic polymer Dyneon THV.png)
RSC Advances
RSC AdvancesIF0
PREAI
分享收藏Multi-feature fusion: Graph neural network and CNN combining for hyperspectral image classification多特征融合: 图神经网络与CNN相结合的高光谱图像分类NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏分享收藏MLFNet: Monocular lifting fusion network for 6DoF texture-less object pose estimationMLFNet: 用于6DoF无纹理物体姿态估计的单目提升融合网络NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容