AI Paper Atlas

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

Syncretic Modality Collaborative Learning for Visible Infrared Person Re-Identification

Ziyu Wei, Xi Yang, Nannan Wang, Xinbo Gao

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification · 227 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 challenge enhanced homogeneity learning (CEHL) (ablation)baseline with SMGM · SYSU-MM01 / RegDBmAP: +0.52% on SYSU-MM01, +2.88% on RegDBImproved
add auxiliary distributional similarity learning (ADSL) (ablation)baseline with CEHL · SYSU-MM01rank-1 and mAP: +3.19% rank-1, +3.91% mAPImproved
add incremental training (IT) strategy (ablation)SMCL without IT · SYSU-MM01rank-1: 63.16 -> 67.39Improved
add incremental training (IT) strategy (ablation)SMCL without IT · RegDBmAP: 73.85 -> 78.57Improved
add an auxiliary modality of any kind (ablation)SMCL · SYSU-MM01mAP: at least 4.64% higherImproved
use syncretic modality instead of grayscale modality (ablation)SMCL · SYSU-MM01rank-1: +3.16%Improved
use syncretic modality instead of X modality (ablation)SMCL · RegDBmAP: +5.57%Improved
use grayscale modality instead of no auxiliary modality (ablation)SMCL · RegDBrank-1: 78.49 -> 74.36Hurt
use grayscale modality instead of X modality (ablation)SMCL · SYSU-MM01 vs RegDBrank-1: 64.23 vs 62.34 on SYSU-MM01; 74.36 vs 79.46 on RegDBMixed
set CEHL difficulty margin m to 4 instead of 0 (ablation)CEHL · SYSU-MM01rank-1: 67.39Improved
use large margin m instead of m=1 (ablation)CEHL · RegDBrank-1: 83.05 at m=1Hurt
use ADSL instead of batch-hard triplet loss (ablation)metric learning · SYSU-MM01rank-1: 61.53 -> 67.39Improved

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