AI Paper Atlas

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

Learning by Aligning: Visible-Infrared Person Re-Identification Using Cross-Modal Correspondences

Hyunjong Park, Sanghoon Lee, Junghyup Lee, Bumsub Ham

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification · 325 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 ID consistency loss with CMAlign (ablation)ID-loss baseline · SYSU-MM01 all-search (ablation)mAP (%): 49.54 -> 52.88Improved
add dense triplet loss with co-attention map and CMAlign (ablation)ID-loss baseline · SYSU-MM01 all-search (ablation)mAP (%): 49.54 -> 51.23Improved
add dense triplet loss without co-attention map (ablation)ID-loss baseline · SYSU-MM01 all-search (ablation)mAP (%): 49.54 -> 50.08No clear effect
add co-attention map to dense triplet loss (with ID consistency) (ablation)L_IC + L_DT · SYSU-MM01 all-search (ablation)mAP (%): 52.78 -> 54.14Improved
add co-attention map to dense triplet loss (with ID consistency) (ablation)L_IC + L_DT · SYSU-MM01 all-search (ablation)rank-1 (%): 53.44 -> 55.41Improved
add dense triplet loss with co-attention to ID consistency loss (ablation)L_IC · SYSU-MM01 all-search (ablation)mAP (%): 52.88 -> 54.14Improved
add ID consistency loss to dense triplet loss with co-attention (ablation)L_DT + A · SYSU-MM01 all-search (ablation)mAP (%): 51.23 -> 54.14Improved
add CMAlign at both conv4-6 and conv5-3 instead of conv4-6 only (ablation)full model · SYSU-MM01 all-search (ablation)mAP (%): 53.02 -> 54.14Improved
add CMAlign at both conv4-6 and conv5-3 instead of conv5-3 only (ablation)full model · SYSU-MM01 all-search (ablation)mAP (%): 53.81 -> 54.14Improved
use ours instead of DDAG on indoor-searchOurs · SYSU-MM01 indoor-searchmAP (%): 67.98 -> 66.33Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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