AI Paper Atlas

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

Unsupervised Visible-Infrared Person Re-Identification via Progressive Graph Matching and Alternate Learning

Zesen Wu, Mang Ye

CVPR 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification · 96 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 PGM and ACCL to DCL baseline (ablation)unsupervised VI-ReID · SYSU-MM01 All searchr1(%): 39.98 -> 57.27Improved
replace PGM with bidirectional combined loss vs alternate Laccl (ablation)ACCL · SYSU-MM01 All searchr1(%): 51.12 -> 57.27Improved
alternate unidirectional cross contrastive learning (Laccl) vs combined bidirectional Lccl (ablation)BGM setting · SYSU-MM01 All searchr1(%): 45.52 -> 51.98Improved
progressive graph matching instead of basic graph matching (ablation)cross-modality correspondence mining · SYSU-MM01 All searchr1(%): 48.82 -> 51.98 (BGM vs PGM with Laccl, rows 2 vs 3 style)Improved
progressive graph matching instead of direct matching (DM) (ablation)correspondence accuracy · SYSU-MM01 All searchmatching accuracyImproved
add PGM+ACCL to DCL baseline (ablation)unsupervised VI-ReID · RegDB Visible to Thermalr1(%): 43.78 -> 69.48Improved
set cross-modality weight mu to 0 (no ACCL) (ablation)ACCL loss weight · SYSU-MM01 All searchr1(%): 57.27 at mu=0.5 -> 39.98 at mu=0 (approx. DCL-only)Hurt
vary mu in {0.3,0.5,0.7,1.0} (ablation)ACCL loss weight · SYSU-MM01 All searchr1(%): 55.03 to 57.27 across mu in 0.3-1.0 rangeNo clear effect

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