Local Convolutional Neural Networks for Person Re-Identification

Jiwei Yang, Xu Shen, Xinmei Tian, Houqiang Li, Jianqiang Huang, Xian-Sheng Hua

Abstract

Recent works have shown that person re-identification can be substantially improved by introducing attention mechanisms, which allow learning both global and local representations. However, all these works learn global and local features in separate branches. As a consequence, the interaction/boosting of global and local information are not allowed, except in the final feature embedding layer. In this paper, we propose local operations as a generic family of building blocks for synthesizing global and local information in any layer. This building block can be inserted into any convolutional networks with only a small amount of prior knowledge about the approximate locations of local parts. For the task of person re-identification, even with only one local block inserted, our local convolutional neural networks (Local CNN) can outperform state-of-the-art methods consistently on three large-scale benchmarks, including Market-1501, CUHK03, and DukeMTMC-ReID.
BibTeX
@inproceedings{yang2018local,
  author = {Jiwei Yang and Xu Shen and Xinmei Tian and Houqiang Li and Jianqiang Huang and Xian-Sheng Hua},
  title = {{Local Convolutional Neural Networks for Person Re-Identification}},
  booktitle = {ACM Multimedia},
  year = {2018},
  doi = {10.1145/3240508.3240645},
}

Loading related content...

Figure