MGN + CircleLoss(ours)

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-IdentificationonMSMT17
Rank-1· 2020-02-25
76.9
best: 91.7 (SOLIDER (with re-ranking))
Circle Loss: A Unified Perspective of Pair Similarity Optimization arXiv:2002.10857
Person Re-IdentificationonMSMT17
mAP· 2020-02-25
52.1
best: 86.7 (CLIP-ReID (with re-ranking))
Circle Loss: A Unified Perspective of Pair Similarity Optimization arXiv:2002.10857
Person Re-IdentificationonMarket-1501
Rank-1· 2020-02-25
96.1
best: 98 (st-ReID(RE, RK))
Circle Loss: A Unified Perspective of Pair Similarity Optimization arXiv:2002.10857
Person Re-IdentificationonMarket-1501
mAP· 2020-02-25
87.4
best: 96.21 (Unsupervised Pre-training (ResNet101+RK))
Circle Loss: A Unified Perspective of Pair Similarity Optimization arXiv:2002.10857