AI Paper Atlas

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

MFEN: Multi-Frequency Expert Network for Visible-Infrared Person Re-ID

Xulin Li, Yan Lu, Bin Liu, Qinhong Yang, Qi Chu, Tao Gong, Nenghai Yu

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification

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 Random Frequency Augmentation (ablation)MFEN baseline (ResNet-50) · SYSU-MM01 All-SearchRank-1: 71.85 -> 75.01Improved
add Multi-Frequency Expert Network (ablation)MFEN baseline with RFA · SYSU-MM01 All-SearchRank-1: 75.01 -> 78.42Improved
add Frequency Auxiliary Optimization (ablation)MFEN with RFA · SYSU-MM01 All-SearchRank-1: 78.42 -> 80.93Improved
use RFA instead of no augmentation (ablation)MFEN · SYSU-MM01 All-SearchRank-1: 77.41 -> 80.93Improved
use RFA instead of CAJ channel augmentation (ablation)MFEN · SYSU-MM01 All-SearchRank-1: 79.88 -> 80.93Improved
use MFEN instead of SE block (ablation)MFEN · SYSU-MM01 All-SearchRank-1: 76.90 -> 80.93Improved
use MFEN instead of CBAM (ablation)MFEN · SYSU-MM01 All-SearchRank-1: 75.45 -> 80.93Improved
use MFEN instead of Non-Local block (ablation)MFEN · SYSU-MM01 All-SearchRank-1: 78.96 -> 80.93Improved
use four frequency experts instead of one full-spectrum expert (ablation)MFEN · SYSU-MM01 All-SearchRank-1: 79.87 -> 80.93Improved
insert MFEN after layer 4 instead of layers 2 and 3 (ablation)MFEN · SYSU-MM01 All-SearchRank-1: 80.93 -> 76.42Hurt
use frequency-enhanced identity loss (f'' second-order term) instead of L_id (ablation)FAO · SYSU-MM01 All-SearchRank-1: 67.80 -> 69.02Improved
use frequency KL loss instead of spatial KL loss (ablation)FAO · SYSU-MM01 All-SearchRank-1: 76.23 -> 78.05Improved

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