Unsupervised Cross-Dataset Transfer Learning for Person Re-Identification

Peixi Peng, Tao Xiang, Yaowei Wang, Massimiliano Pontil, Shaogang Gong, Tiejun Huang, Yonghong Tian

CVPR 2016

doi:10.1109/CVPR.2016.146 /cvpr/2016/peng2016cvpr-unsupervised/

Abstract

Most existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training. This severely limits their scalability in real-world applications. To overcome this limitation, we develop a novel cross-dataset transfer learning approach to learn a discriminative representation. It is unsupervised in the sense that the target dataset is completely unlabelled. Specifically, we present an multi-task dictionary learning method which is able to learn a dataset-shared but target-data-biased representation. Experimental results on five benchmark datasets demonstrate that the method significantly outperforms the state-of-the-art.

PDF CVPR Semantic Scholar

Cite

Text

Peng et al. "Unsupervised Cross-Dataset Transfer Learning for Person Re-Identification." Conference on Computer Vision and Pattern Recognition, 2016. doi:10.1109/CVPR.2016.146

Markdown

[Peng et al. "Unsupervised Cross-Dataset Transfer Learning for Person Re-Identification." Conference on Computer Vision and Pattern Recognition, 2016.](https://mlanthology.org/cvpr/2016/peng2016cvpr-unsupervised/) doi:10.1109/CVPR.2016.146

BibTeX

@inproceedings{peng2016cvpr-unsupervised,
  title     = {{Unsupervised Cross-Dataset Transfer Learning for Person Re-Identification}},
  author    = {Peng, Peixi and Xiang, Tao and Wang, Yaowei and Pontil, Massimiliano and Gong, Shaogang and Huang, Tiejun and Tian, Yonghong},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2016},
  doi       = {10.1109/CVPR.2016.146},
  url       = {https://mlanthology.org/cvpr/2016/peng2016cvpr-unsupervised/}
}