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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Random Frequency Augmentation (ablation) | MFEN baseline (ResNet-50) · SYSU-MM01 All-Search | Rank-1: 71.85 -> 75.01 | Improved |
| add Multi-Frequency Expert Network (ablation) | MFEN baseline with RFA · SYSU-MM01 All-Search | Rank-1: 75.01 -> 78.42 | Improved |
| add Frequency Auxiliary Optimization (ablation) | MFEN with RFA · SYSU-MM01 All-Search | Rank-1: 78.42 -> 80.93 | Improved |
| use RFA instead of no augmentation (ablation) | MFEN · SYSU-MM01 All-Search | Rank-1: 77.41 -> 80.93 | Improved |
| use RFA instead of CAJ channel augmentation (ablation) | MFEN · SYSU-MM01 All-Search | Rank-1: 79.88 -> 80.93 | Improved |
| use MFEN instead of SE block (ablation) | MFEN · SYSU-MM01 All-Search | Rank-1: 76.90 -> 80.93 | Improved |
| use MFEN instead of CBAM (ablation) | MFEN · SYSU-MM01 All-Search | Rank-1: 75.45 -> 80.93 | Improved |
| use MFEN instead of Non-Local block (ablation) | MFEN · SYSU-MM01 All-Search | Rank-1: 78.96 -> 80.93 | Improved |
| use four frequency experts instead of one full-spectrum expert (ablation) | MFEN · SYSU-MM01 All-Search | Rank-1: 79.87 -> 80.93 | Improved |
| insert MFEN after layer 4 instead of layers 2 and 3 (ablation) | MFEN · SYSU-MM01 All-Search | Rank-1: 80.93 -> 76.42 | Hurt |
| use frequency-enhanced identity loss (f'' second-order term) instead of L_id (ablation) | FAO · SYSU-MM01 All-Search | Rank-1: 67.80 -> 69.02 | Improved |
| use frequency KL loss instead of spatial KL loss (ablation) | FAO · SYSU-MM01 All-Search | Rank-1: 76.23 -> 78.05 | Improved |
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.
- PartMix — PartMix: Regularization Strategy To Learn Part Discovery for Visible-Infrared Person Re-Identification (CVPR 2023) · better on 1 of 1 shared result
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
- Spatial-Frequency Collaborative Learning for Occluded Visible-Infrared Person Re-Identification (CVPR 2026 · similarity 0.88)
- High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-identification (AAAI 2024 · similarity 0.88)
- Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification (NeurIPS 2024 · similarity 0.86)
- Empowering Visible-Infrared Person Re-Identification with Large Foundation Models (NeurIPS 2024 · similarity 0.86)
- Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.86)
- Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.86)
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.
