A GENERAL RE-RANKING METHOD BASED ON METRIC LEARNING FOR PERSON RE-IDENTIFICATION
Tongkun Xu, Xin Zhao, Jiamin Hou, Jiyong Zhang, Xinhong Hao, Jian Yin
-
Members: FreeSPS
IEEE Members: $11.00
Non-members: $15.00Length: 08:14
08 Jul 2020
When Person Re-identification is considered as a retrieval task, re-ranking becomes a critical part of improving the reidentification accuracy. Most of the existing re-ranking methods focus on k-nearest neighbors, which requires a lot of queries and memory. In this paper, we propose a Feature Relation Map based Similarity Evaluation (FRM-SE) model to tackle this problem. The Feature Relation Map is utilized to automatically mine the latent relation between the k-neighbors through convolution operation. The re-ranking distance is learned through the FRM-SE model with metric learning. Further, we optimize the existing re-ranking method to utilize the advantage of the FRM-SE model for maintaining a balance between accuracy and complexity.
The proposed approach is validated on two benchmark datasets, Market1501 and CUHK03. Results show that our reranking method is superior to the state-of-the-art re-ranking methods. Furthermore, in the transfer learning setting, the model trained on either Market1501 or CUHK03 can achieve a comparable accuracy improvement on the DuekMTMC dataset, which validates the generalization of our SE model.
The proposed approach is validated on two benchmark datasets, Market1501 and CUHK03. Results show that our reranking method is superior to the state-of-the-art re-ranking methods. Furthermore, in the transfer learning setting, the model trained on either Market1501 or CUHK03 can achieve a comparable accuracy improvement on the DuekMTMC dataset, which validates the generalization of our SE model.