A deep model with combined losses for person re-identification |
| |
| Institution: | 1. Institute of Machine Learning and Systems Biology, School of Electronics and Information Engineering, Tongji University, Caoan Road 4800, Shanghai 201804, China;2. Science Computing and Intelligent Information Processing of Guang Xi Higher Education Key Laboratory, Guangxi Teachers Education University, Nanning, Guangxi 530001, China;1. School of Electronics and Information Engineering, Southwest University, Chongqing 400715, China;2. College of Computer Science, Chongqing University, Chongqing 400044, China;3. School of Information Technology, Jiangxi University of Finance and Economics, Nanchang 330013, China;4. School of Economics and Business Administration, Chongqing University, Chongqing 400044, China |
| |
| Abstract: | Person re-identification (PReID), which aims to re-identity a pedestrian from multiple non-overlapping cameras, has been significantly improved by deep learning system. There exist two popular deep frameworks used for PReID, i.e., identification and triplet models. Since these two frameworks have different loss functions, they have their own advantages and disadvantages. To combine the both advantages of two frameworks, in this paper, we propose using the triplet and Online Instance Matching (OIM) losses to train the carefully designed network. Given a triplet input images, the combined model can output the identities of the input images and learn a corresponding similarity measurement simultaneously. Experiments on CUHK01, CUHK03, Market-1501, and DukeMTMC-reID datasets demonstrate that the proposed model outperforms the compared state-of-the-art methods in most cases. |
| |
| Keywords: | Convolutional Neural Networks Person Re-identification |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
