Towards unsupervised open-set person re-identification

Hanxiao Wang, Xiatian Zhu, Tao Xiang, Shaogang Gong

Abstract

Most existing person re-identification (ReID) methods assume the availability of extensively labelled cross-view person pairs and a closed-set scenario (i.e. all the probe people exist in the gallery set). These two assumptions significantly limit their usefulness and scalability in real-world applications, particularly with large scale camera networks. To overcome the limitations, we introduce a more challenging yet realistic ReID setting termed OneShot-OpenSet-RelD, and propose a novel Regularised Kernel Subspace Learning model for ReID under this setting. Our model differs significantly from existing ReID methods due to its ability of effectively learning cross-view identity-specific information from unlabelled data alone, and its flexibility of naturally accommodating pairwise labels if available.
BibTeX
@inproceedings{wang2016towards,
  author = {Hanxiao Wang and Xiatian Zhu and Tao Xiang and Shaogang Gong},
  title = {{Towards unsupervised open-set person re-identification}},
  booktitle = {ICIP},
  year = {2016},
  doi = {10.1109/icip.2016.7532461},
}

Loading related content...

Figure