首页|Self-supervised recalibration network for person re-identification

Self-supervised recalibration network for person re-identification

扫码查看
原文链接
  • 万方数据
  • 维普
The attention mechanism can extract salient features in images,which has been proved to be effective in improving the performance of person re-identification(Re-ID).However,most of the existing attention modules have the following two shortcomings:On the one hand,they mostly use global average pooling to generate context descriptors,without highlighting the guiding role of salient information on descriptor generation,resulting in insufficient ability of the final generated attention mask representa-tion;On the other hand,the design of most attention modules is complicated,which greatly increases the computational cost of the model.To solve these problems,this paper proposes an attention module called self-supervised recalibration(SR)block,which introduces both global and local information through adaptive weighted fusion to generate a more refined attention mask.In particular,a special"Squeeze-Excitation"(SE)unit is designed in the SR block to further process the generated intermediate masks,both for nonlinearizations of the features and for constraint of the resulting computation by controlling the number of channels.Furthermore,we combine the most commonly used ResNet-50 to construct the instantiation model of the SR block,and verify its effectiveness on multiple Re-ID datasets,especially the mean Average Precision(mAP)on the Occluded-Duke dataset exceeds the state-of-the-art(SOTA)algorithm by 4.49％.

Person re-identificationAttention mechanismGlobal informationLocal informationAdaptive weighted fusion

Shaoqi Hou、Zhiming Wang、Zhihua Dong、Ye Li、Zhiguo Wang、Guangqiang Yin、Xinzhong Wang

展开 >

Shenzhen Institute of Information Technology,Shenzhen,518172,China

University of Electronic Science and Technology of China,Chengdu,611731,China

Kash Institute of Electronics and Information Industry,Kashi,844099,China

Natural Science Foundation of Xinjiang Uygur Autonomous RegionNatural Science Foundation of Xinjiang Uygur Autonomous Region

2022D01B1862022D01B05

2024

10.1016/j.dt.2023.01.011

防务技术
中国兵工学会

防务技术

CSTPCD
影响因子：0.358
ISSN：2214-9147
年,卷(期)：2024.(1)
  • 61