SCIENCE CHINA Information Sciences, Volume 64 , Issue 2 : 120111(2021) https://doi.org/10.1007/s11432-019-2943-6

## Learning generalizable deep feature using triplet-batch-center loss for person re-identification

• AcceptedMay 9, 2020
• PublishedOct 27, 2020
Share
Rating

### Acknowledgment

This work was supported by Zhejiang Lab (Grant No. 2019NB0AB02) and National Natural Science Foundation of China (NSFC) (Grant Nos. 61876212, 61733007, 6157220).

### References

[1] Yu Y, Ji Z, Guo J. Zero-Shot Learning via Latent Space Encoding. IEEE Trans Cybern, 2019, 49: 3755-3766 CrossRef Google Scholar

[2] He X W, Zhou Y, Zhou Z C, et al. Triplet-center loss for multi-view 3d object retrieval. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2018. 1945--1954. Google Scholar

[3] Song C F, Huang Y, Ouyang W L, et al. Mask-guided contrastive attention model for person re-identification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2018. 1179--1188. Google Scholar

[4] Xu J, Zhao R, Zhu F, et al. Attention-aware compositional network for person re-identification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2018. 2119--2128. Google Scholar

[5] Liu J X, Ni B B, Yan Y C, et al. Pose transferrable person re-identification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2018. 4099--4108. Google Scholar

[6] Sarfraz M S, Schumann A, Eberle A, et al. A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-rankin. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2018. 420--429. Google Scholar

[7] Li W, Zhu X T, Gong S G. Harmonious attention network for person re-identification. In: Proceedings of IEEE conference on computer vision and pattern recognition, 2018. 2285--2294. Google Scholar

[8] Wang C, Zhang Q, Huang C, et al. Mancs: a multi-task attentional network with curriculum sampling for person re-identification. In: Proceedings of European Conference on Computer Vision (ECCV), 2018. 365--381. Google Scholar

[9] Fan X, Jiang W, Luo H. SphereReID: Deep hypersphere manifold embedding for person re-identification. J Visual Communication Image Representation, 2019, 60: 51-58 CrossRef Google Scholar

• Table 1

Table 1Performance (%) comparisons by state-of-the-art methods$^{\rm~a)}$

 2*Method Market1501 CUHK03 (labeled) CUHK03 (detected) DukeMTMC-reID Rank-1 mAP Rank-1 mAP Rank-1 mAP Rank-1 mAP MGCAM [3] 84.8 74.3 50.1 50.2 46.7 46.9 – – AACN [4] 85.9 66.9 – – – – 76.8 59.3 Pose transfer [5] 87.7 68.9 33.8 30.5 30.1 28.2 68.6 48.4 PSE [6] 87.7 69.0 – – 30.2 27.3 79.8 62.0 HA-CNN [7] 91.2 75.7 44.4 41.0 41.7 38.6 80.5 63.8 Mancs [8] 93.1 82.3 69.0 63.9 65.5 60.5 84.9 71.8 SphereReID [9] 94.4 83.6 66.8* 65.7* 66.1* 63.6* 83.9 68.5 series TBCL 94.2 84.8 75.9 73.3 72.7 70.5 85.8 74.0

a) Bold numbers denote the best performance. $*$ represents the result of the implementation.

Citations

Altmetric