首页|Not Every Patch is Needed: Toward a More Efficient and Effective Backbone for Video-Based Person Re-Identification
Not Every Patch is Needed: Toward a More Efficient and Effective Backbone for Video-Based Person Re-Identification
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
IEEE
This paper proposes a new effective and efficient plug-and-play backbone for video-based person re-identification (ReID). Conventional video-based ReID methods typically use CNN or transformer backbones to extract deep features for every position in every sampled video frame. Here, we argue that this exhaustive feature extraction could be unnecessary, since we find that different frames in a ReID video often exhibit small differences and contain many similar regions due to the relatively slight movements of human beings. Inspired by this, a more selective, efficient paradigm is explored in this paper. Specifically, we introduce a patch selection mechanism to reduce computational cost by choosing only the crucial and non-repetitive patches for feature extraction. Additionally, we present a novel network structure that generates and utilizes pseudo frame global context to address the issue of incomplete views resulting from sparse inputs. By incorporating these new designs, our backbone can achieve both high performance and low computational cost. Extensive experiments on multiple datasets show that our approach reduces the computational cost by 74% compared to ViT-B and 28% compared to ResNet50, while the accuracy is on par with ViT-B and outperforms ResNet50 significantly.
Feature extractionTransformersComputational efficiencyData miningCostsComputer visionResidual neural networksOptical flowIdentification of personsCorrelation
Lanyun Zhu、Tianrun Chen、Deyi Ji、Jieping Ye、Jun Liu
展开 >
Information Systems Technology and Design Pillar, Singapore University of Technology and Design, Tampines, Singapore
College of Computer Science and Technology, Zhejiang University, Hangzhou, China
Alibaba Group, Hangzhou, China
School of Computing and Communications, Lancaster University, Lancaster, U.K.
NETL
NSTL
IEEE
