AI Paper Atlas

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

Explainable Person Re-Identification With Attribute-Guided Metric Distillation

Xiaodong Chen, Xinchen Liu, Wu Liu, Xiao-Ping Zhang, Yongdong Zhang, Tao Mei

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 53 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 interpreter distance re-weighting (ablation)SBS (R101) · DukeMTMC-ReIDRank-1 / mAP: 89.3 -> 90.2; 78.4 -> 79.1Improved
add interpreter distance re-weighting (ablation)SBS (R50) · DukeMTMC-ReIDRank-1 / mAP: 88.2 -> 89.1; 75.5 -> 75.6Improved
add interpreter distance re-weighting (ablation)BOT (R50) · Market-1501Rank-1 / mAP: 93.8 -> 94.4; 84.7 -> 86.1Improved
add interpreter distance re-weighting (ablation)OSNet · Market-1501Rank-1 / mAP: 94.7 -> 95.0; 85.7 -> 86.1Improved
replace target model with attribute-guided interpreterSBS (ResNet-50) · M->D cross-domainRank-1 / mAP: 45.02 -> 47.08; 26.43 -> 28.41Improved
replace target model with attribute-guided interpreterSBS (ResNet-50) · D->M cross-domainRank-1 / mAP: 53.15 -> 54.48; 24.48 -> 25.48Improved
distill metric into interpreter (in-domain)SBS (ResNet-101) · Market-1501Rank-1: 95.94 -> 95.55Hurt
distill metric into interpreter (in-domain)SBS (ResNet-34) · Market-1501Rank-1: 93.94 -> 94.21No clear effect
share 3 stages instead of 1 with target model (ablation)interpreter · Market-1501Rank-1: 94.76 -> 94.74No clear effect
share 5 stages instead of 3 (ablation)interpreter · Market-1501Rank-1: 94.74 -> 94.89No clear effect
share 2 stages instead of 3 (ablation)interpreter · Market-1501Rank-1: 94.74 -> 93.98Hurt

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