Auto-ReID (ICCV'19)

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-IdentificationonCUHK03 detected
MAP· 2019-03-23
69.3
best: 86.9 (Top-DB-Net + RK)
Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification arXiv:1903.09776
Person Re-IdentificationonCUHK03 detected
Rank-1· 2019-03-23
73.3
best: 85.7 (Top-DB-Net + RK)
Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification arXiv:1903.09776
Person Re-IdentificationonCUHK03 labeled
MAP· 2019-03-23
73
best: 89.29 (Weakly Pre-training (ResNet101+RK))
Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification arXiv:1903.09776
Person Re-IdentificationonCUHK03 labeled
Rank-1· 2019-03-23
77.9
best: 87.86 (Weakly Pre-training (ResNet101+RK))
Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification arXiv:1903.09776