LuNet (RK)

Reported on 6 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 Vision6 results

Person Re-IdentificationonMarket-1501
Rank-1· 2017-03-22
84.59
best: 98 (st-ReID(RE, RK))
In Defense of the Triplet Loss for Person Re-Identification arXiv:1703.07737
Person Re-IdentificationonMarket-1501
Rank-5· 2017-03-22
91.89
best: 98.9 (st-ReID(RE, RK))
In Defense of the Triplet Loss for Person Re-Identification arXiv:1703.07737
Person Re-IdentificationonMarket-1501
mAP· 2017-03-22
75.62
best: 96.21 (Unsupervised Pre-training (ResNet101+RK))
In Defense of the Triplet Loss for Person Re-Identification arXiv:1703.07737
Person Re-IdentificationonMARS
Rank-1· 2017-03-22
78.48
best: 90.8 (DenseIL)
In Defense of the Triplet Loss for Person Re-Identification arXiv:1703.07737
Person Re-IdentificationonMARS
Rank-5· 2017-03-22
88.74
best: 97.23 (PiT)
In Defense of the Triplet Loss for Person Re-Identification arXiv:1703.07737
Person Re-IdentificationonMARS
mAP· 2017-03-22
73.68
best: 88.5 (B-BOT + OSM + CL Centers* (Re-rank))
In Defense of the Triplet Loss for Person Re-Identification arXiv:1703.07737