Research map / Label-efficient and robust learning / Recognition and long-tail
MRCN: A Novel Modality Restitution and Compensation Network for Visible-Infrared Person Re-identification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 MRCN to the baseline (ablation) | VI-ReID model · RegDB | Rank-1: 78.2 -> 91.4 | Helped |
| Add MRCN to the baseline (ablation) | VI-ReID model · SYSU-MM01 | Rank-1: 60.7 -> 68.9 | Helped |
| Add the CQC loss (ablation) | MRCN · RegDB | Rank-1: 85.5 -> 91.4 | Helped |
| Add the CQC loss (ablation) | MRCN · SYSU-MM01 | Rank-1: 64.6 -> 68.9 | Helped |
| Add MRM to MCM (ablation) | MRCN · RegDB | Rank-1: 89.7 -> 91.4 | Helped |
| Add MRM to MCM (ablation) | MRCN · SYSU-MM01 | Rank-1: 64.4 -> 68.9 | Helped |
| Add MCM to MRM (ablation) | MRCN · RegDB | Rank-1: 90.3 -> 91.4 | Helped |
| Add MCM to MRM (ablation) | MRCN · SYSU-MM01 | Rank-1: 66.8 -> 68.9 | Helped |
| Plug MRCN after stage-0 instead of stage-1 (ablation) | MRCN with ResNet-50 · RegDB | Rank-1: 91.4 -> 87.8 | Hurt |
| Plug MRCN after stage-2 instead of stage-1 (ablation) | MRCN with ResNet-50 · RegDB | Rank-1: 91.4 -> 88.1 | Hurt |
| Plug MRCN after stage-3 instead of stage-1 (ablation) | MRCN with ResNet-50 · RegDB | Rank-1: 91.4 -> 73.5 | Hurt |
| Plug MRCN after stage-4 instead of stage-1 (ablation) | MRCN with ResNet-50 · RegDB | Rank-1: 91.4 -> 72.0 | Hurt |
Closest papers by meaning
- Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.92)
- Empowering Visible-Infrared Person Re-Identification with Large Foundation Models (NeurIPS 2024 · similarity 0.91)
- Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.90)
- High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-identification (AAAI 2024 · similarity 0.90)
- TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification (AAAI 2025 · similarity 0.90)
- Relieving Universal Label Noise for Unsupervised Visible-Infrared Person Re-Identification by Inferring from Neighbors (AAAI 2025 · similarity 0.88)
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.