Weakly Supervised Pre-training (ResNet50+BDB)

Reported on 2 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 Vision2 results

Person Re-IdentificationonCUHK03
MAP· 2022-03-30
82.3
best: 94.3 (Proposed SGGNN)
Large-Scale Pre-training for Person Re-identification with Noisy Labels arXiv:2203.16533
Person Re-IdentificationonCUHK03
Rank-1· 2022-03-30
84.7
best: 97.8 (AlignedReID (RK))
Large-Scale Pre-training for Person Re-identification with Noisy Labels arXiv:2203.16533