AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Bridging the Source-to-Target Gap for Cross-Domain Person Re-identification with Intermediate Domains

Yongxing Dai, Yifan Sun, Jun Liu, Zekun Tong, Ling‐Yu Duan

IJCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 24 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 the diversity loss L_div to IDM++ (ablation)Baseline2 + IDM++ · Market-1501->DukeMTMC-reIDRank-1: 1.1% lower than the full method without itImproved
add the bridge loss L_bridge^phi to IDM++ (ablation)Baseline2 + IDM++ · Market-1501->DukeMTMC-reIDmAP/Rank-1: 3.2%/2.5% lower without itImproved
add the bridge loss L_bridge^f to IDM++ (ablation)Baseline2 + IDM++ · Market-1501->DukeMTMC-reIDmAP/Rank-1: 1.0%/1.6% lower without itImproved
add MGM (domain mapping with consistency loss) on top of IDM (ablation)Baseline2 + IDM · Market-1501->DukeMTMC-reIDmAP/Rank-1: 70.5 -> 73.2 mAP; 2.7%/1.9% higherImproved
add IDM++ to the strong baselineBaseline2 · Market-1501->DukeMTMC-reIDmAP/Rank-1: 7.4%/5.4% higherImproved
add IDM++ to the naive baselineBaseline1 · Market-1501->DukeMTMC-reIDmAP/Rank-1: 8.2% and 5.0% higherImproved
add MGM to IDM (ablation)IDM · Market-1501->MSMT17mAP/Rank-1: up to 6.7% mAP and 8.6% Rank-1Improved
use IDM++ instead of prior best CCLIDM++ vs CCL · Market-1501->MSMT17mAP: 4.4% mAPImproved
use IDM++ instead of CCLIDM++ vs CCL · DukeMTMC-reID->MSMT17mAP: 36.3 -> 40.5Improved
add XBM memory-bank hard negative mining (Strong vs Naive baseline) (ablation)Baseline1 · Market-1501->DukeMTMC-reIDmAP: 63.4 -> 65.8Improved
add IDM++ over IDM with synthetic source UnrealIDM · Unreal->MSMT17mAP: 38.3 -> 41.5Improved

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