AI Paper Atlas

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

Exploring Homogeneous and Heterogeneous Consistent Label Associations for Unsupervised Visible-Infrared Person ReID

Lingfeng He, De Cheng, Nannan Wang, Xinbo Gao

IJCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification · 28 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 cross-modality loss L_CM (MULT) to the baseline (ablation)Baseline · SYSU-MM01 all-searchmAP / Rank-1: +16.35% mAP, +18.26% Rank-1Improved
train within entire AMIRL framework with MULT (ablation)Baseline · SYSU-MM01 all-searchmAP / Rank-1: +20.66% mAP, +23.01% Rank-1Improved
add OCLR directly to the baseline (ablation)Baseline · SYSU-MM01 all-searchmAP / Rank-1: +12.46% mAP, +12.58% Rank-1Improved
add OCLR to AMIRL framework (ablation)Baseline + L_IM + L_CM · SYSU-MM01 all-searchmAP / Rank-1: +3.71% mAP, +4.59% Rank-1Improved
add AMIRL (intra-modality memory structure) without OCLR (ablation)Baseline + L_CM · SYSU-MM01 all-searchmAP: +0.60% mAPImproved
add AMIRL with OCLR (ablation)Baseline + L_CM + L_OCLR · SYSU-MM01 all-searchmAP: +2.41% mAPImproved
use both intra and auxiliary memory instead of intra only (ablation)Ours · SYSU-MM01 all-searchRank-1: 63.77 -> 64.77Improved
use both intra and auxiliary memory instead of auxiliary only (ablation)Ours · SYSU-MM01 all-searchRank-1: 63.06 -> 64.77Improved
use AMIRL instead of MIRL (ablation)Ours · SYSU-MM01 all-searchRank-1: 64.05 -> 64.77Improved
model heterogeneous relation S^he with optimal transport instead of Jaccard (ablation)Ours · SYSU-MM01 all-searchRank-1: 61.08 -> 64.77Improved
model S^he with optimal transport instead of cosine (k=20) (ablation)Ours · SYSU-MM01 all-searchRank-1: 62.19 -> 64.77Improved
add channel augmentation (CA) to OCLR (ablation)Ours · SYSU-MM01 all-searchRank-1: 61.98 -> 64.77Improved

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