LDS (ResNet50 + RK)

Reported on 4 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Person Re-IdentificationonMarket-1501
Rank-1· 2021-11-10
96.17
best: 98 (st-ReID(RE, RK))
Learning to Disentangle Scenes for Person Re-identification arXiv:2111.05476
Person Re-IdentificationonMarket-1501
mAP· 2021-11-10
94.89
best: 96.21 (Unsupervised Pre-training (ResNet101+RK))
Learning to Disentangle Scenes for Person Re-identification arXiv:2111.05476
Person Re-IdentificationonDukeMTMC-reID
Rank-1· 2021-11-10
92.91
best: 95.6 (CTL Model (ResNet50, 256x128))
Learning to Disentangle Scenes for Person Re-identification arXiv:2111.05476
Person Re-IdentificationonDukeMTMC-reID
mAP· 2021-11-10
91
best: 97.1 (DenseIL)
Learning to Disentangle Scenes for Person Re-identification arXiv:2111.05476