AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

MVP Matching: A Maximum-Value Perfect Matching for Mining Hard Samples, With Application to Person Re-Identification

Han Sun, Zhiyuan Chen, Shiyang Yan, Lin Xu

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 48 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add re-ranking at test timeMVP Loss · Market-1501mAP: 80.5% -> 90.9%Improved
add re-ranking at test timeMVP Loss · Duke-MTMCmAP: 70.0% -> 83.9%Improved
add re-ranking at test timeMVP Loss · CUHK03-DetectedTop-1: 91.8% -> 96.4%Improved
add re-ranking at test timeMVP Loss · CUHK03-LabeledTop-1: 93.7% -> 97.7%Improved
replace batch-hard triplet loss with MVP matching lossResNet-50 metric learning · Market-1501mAP: 76.9% -> 80.5%Improved
replace batch-wise OT loss with MVP matching lossResNet-50 metric learning · MSMT17mAP: 44.5% -> 46.3%Improved
replace batch-wise OT loss with MVP matching lossResNet-50 metric learning · Duke-MTMCmAP: 66.8% -> 70.0%Improved
replace batch-wise OT loss with MVP matching lossResNet-50 metric learning · CUHK03-LabeledTop-1: 92.5% -> 93.7%Improved
replace identification loss with batch-hard triplet lossResNet-50 · Market-1501mAP: 70.4% -> 76.9%Improved
replace identification loss with batch-all triplet lossResNet-50 · MSMT17mAP: 33.9% -> 27.1%Hurt
replace batch-wise OT loss with MVP matching lossResNet-50 metric learning · CUHK03-DetectedTop-5: 98.8% -> 98.8%No clear effect
replace BH triplet, lifted and OT losses with MVP matching lossResNet-50 metric learning · Market-1501, Duke-MTMC, MSMT17, CUHK03-Labeledconvergence speed (mAP / top-1 vs epochs)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy