Exploiting Robust Unsupervised Video Person Re-identification
About
Unsupervised video person re-identification (reID) methods usually depend on global-level features. And many supervised reID methods employed local-level features and achieved significant performance improvements. However, applying local-level features to unsupervised methods may introduce an unstable performance. To improve the performance stability for unsupervised video reID, this paper introduces a general scheme fusing part models and unsupervised learning. In this scheme, the global-level feature is divided into equal local-level feature. A local-aware module is employed to explore the poentials of local-level feature for unsupervised learning. A global-aware module is proposed to overcome the disadvantages of local-level features. Features from these two modules are fused to form a robust feature representation for each input image. This feature representation has the advantages of local-level feature without suffering from its disadvantages. Comprehensive experiments are conducted on three benchmarks, including PRID2011, iLIDS-VID, and DukeMTMC-VideoReID, and the results demonstrate that the proposed approach achieves state-of-the-art performance. Extensive ablation studies demonstrate the effectiveness and robustness of proposed scheme, local-aware module and global-aware module. The code and generated features are available at https://github.com/deropty/uPMnet.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Video Person Re-ID | iLIDS-VID | Rank-163.1 | 80 | |
| Video Person Re-Identification | DukeMTMC-VideoReID | Rank-1 Accuracy83.6 | 26 | |
| Video Person Re-Identification | PRID 2011 | Rank-1 Accuracy92 | 23 | |
| Video Person Re-Identification | DukeMTMC-VideoReID (test) | Rank-1 Acc83.6 | 7 |