AI Paper Atlas

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

Global Distance-distributions Separation for Unsupervised Person Re-identification

Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 86 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 GDS loss (ablation)clustering Baseline · Market1501→DukeMTMC-reIDmAP: 48.4 -> 52.9Improved
add GDS loss (ablation)clustering Baseline · DukeMTMC-reID→Market1501mAP: 52.1 -> 57.1Improved
add distribution-based hard mining to GDS (ablation)clustering Baseline · Market1501→DukeMTMC-reIDmAP: 52.9 -> 55.1Improved
add distribution-based hard mining to GDS (ablation)clustering Baseline · DukeMTMC-reID→Market1501mAP: 57.1 -> 61.2Improved
add GDS-H lossSPGAN · Market1501→DukeMTMC-reIDmAP: 22.3 -> 27.5Improved
add GDS-H lossSPGAN · DukeMTMC-reID→Market1501mAP: 22.8 -> 29.4Improved
add GDS-H lossB-SNR · Market1501→DukeMTMC-reIDmAP: 54.3 -> 59.7Improved
add GDS-H lossB-SNR · DukeMTMC-reID→Market1501mAP: 66.1 -> 72.5Improved
use momentum coefficient 0.99 instead of 0 (global instead of batch-wise distributions) (ablation)Baseline+GDS-H · Market1501→DukeMTMC-reIDmAP: 51.4 -> 55.1Improved
use momentum coefficient 0.99 instead of 0 (global instead of batch-wise distributions) (ablation)Baseline+GDS-H · DukeMTMC-reID→Market1501mAP: 56.2 -> 61.2Improved
replace Histogram loss with GDS-H loss (ablation)clustering Baseline · Market1501→DukeMTMC-reIDmAP: 50.2 -> 55.1Improved
add GDS-H loss with K-means clusteringBaseline · Market1501→DukeMTMC-reID (K-means)mAP: 40.2 -> 49.0Improved

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