M3L

Reported on 4 benchmarks across 2 tasks · 1 paper

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

Methodology2 results

Domain AdaptationonCUHK03 to Market
R1· 2020-12-01
82.7
best: 93.9 (CORE-ReID V2)
Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification arXiv:2012.00417
Domain AdaptationonCUHK03 to Market
mAP· 2020-12-01
62.4
best: 84.5 (CORE-ReID V2)
Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification arXiv:2012.00417

Other2 results

Unsupervised Domain AdaptationonCUHK03 to Market
R1· 2020-12-01
82.7
best: 93.9 (CORE-ReID V2)
Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification arXiv:2012.00417
Unsupervised Domain AdaptationonCUHK03 to Market
mAP· 2020-12-01
62.4
best: 84.5 (CORE-ReID V2)
Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification arXiv:2012.00417