2023
DOI: 10.11834/jig.220838
|View full text |Cite
|
Sign up to set email alerts
|

Cross-domain unsupervised Re-ID algorithm based on neighbor adversarial and consistency loss

Jinlei Zhu,
Yanfeng Li,
Houjin Chen
et al.

Abstract: Market-1501 (1501 identities dataset from market) 和 DukeMTMC-reID (multi-target multi-camera person re-identification dataset from Duke University)数据集上的 Rank-1 和平均精度均值(mean average precision, mAP) 指标分别达到了 92. 8%、 84. 1% 和 83. 9%、 71. 1%。结论 提出方法设计了邻域对抗损失与邻域连 续性损失函数, 增强了模型对相似人群的辨识能力, 从而有效提升了行人重识别的性能。 关键词: 行人重识别 (Re-ID) ; 无监督学习; 跨域迁移学习; 邻域对抗损失 (NAL) ; 邻域连续损失 (NCL)

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
0
0

Publication Types

Select...

Relationship

0
0

Authors

Journals

citations
Cited by 0 publications
references
References 26 publications
0
0
0
Order By: Relevance

No citations

Set email alert for when this publication receives citations?