• DOI:10.1109/tnnls.2020.2999517
Corpus ID: 195886226

Weakly Supervised Person Re-ID: Differentiable Graphical Learning and a New Benchmark.

@article{Wang2020WeaklySP,
  title={Weakly Supervised Person Re-ID: Differentiable Graphical Learning and a New Benchmark.},
  author={Guangrun Wang and Guangcong Wang and Xujie Zhang and Jianhuang Lai and Zhengtao Yu and L. Lin},
  journal={IEEE transactions on neural networks and learning systems},
  year={2020},
  volume={PP}
}

Guangrun Wang, Guangcong Wang, +3 authors L. Lin

Published 2020

Computer Science, Medicine

IEEE transactions on neural networks and learning systems

Person re-identification (Re-ID) benefits greatly from the accurate annotations of existing datasets (e.g., CUHK03 \cite{li2014deepreid} and Market-1501 \cite{zheng2015scalable}), which are quite expensive because each image in these datasets has to be assigned with a proper label. [...] Key Method The pseudo label is further used to supervise the learning of the Re-ID model. When compared with the fully supervised Re-ID models, our method achieves the state-of-the-art performance on SYSU-30$k$ and other…Expand Abstract

View on PubMed

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed