Research map / Label-efficient and robust learning / Recognition and long-tail
Modality Synergy Complement Learning with Cascaded Aggregation for Visible-Infrared Person Re-identification
Yiyuan Zhang, Sanyuan Zhao, Yuhao Kang, Jianbing Shen
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 Modality Synergy module (ablation) | AGW* baseline · SYSU-MM01 all-search | Rank-1: 59.82 -> 62.82 | Improved |
| add Modality Synergy module (ablation) | AGW* baseline · SYSU-MM01 all-search | mAP: 56.07 -> 60.25 | Improved |
| add Modality Complement module (ablation) | AGW* baseline · SYSU-MM01 all-search | Rank-1: 59.82 -> 64.84 | Improved |
| add Modality Complement module (ablation) | AGW* baseline · SYSU-MM01 all-search | mAP: 56.07 -> 61.00 | Improved |
| add MC to Base+MS (ablation) | Base+MS · SYSU-MM01 all-search | Rank-1: 62.82 -> 71.16 | Improved |
| add Cascaded Aggregation to Base+MS+MC (ablation) | Base+MS+MC · SYSU-MM01 all-search | Rank-1: 71.16 -> 76.99 | Improved |
| add Cascaded Aggregation to Base+MS+MC (ablation) | Base+MS+MC · SYSU-MM01 all-search | mAP: 66.30 -> 71.64 | Improved |
| add all components (MS, MC, CA) (ablation) | AGW* baseline · SYSU-MM01 all-search | Rank-1: 59.82 -> 76.99 | Improved |
| train with MSCLNet instead of baseline (ablation) | AGW* · feature distance analysis | mean intra-identity distance: 1.31 -> 1.27 | Improved |
| full MSCLNet vs MPANet | MSCLNet · SYSU-MM01 all-search | Rank-1: 70.58 -> 76.99 | Improved |
| full MSCLNet vs MPANet | MSCLNet · RegDB infrared-to-visible | mAP: 80.70 -> 78.31 | Hurt |
Closest papers by meaning
- Modality Unifying Network for Visible-Infrared Person Re-Identification (ICCV 2023 · similarity 0.93)
- Cross-Modality Person Re-identification with Memory-Based Contrastive Embedding (AAAI 2023 · similarity 0.92)
- Empowering Visible-Infrared Person Re-Identification with Large Foundation Models (NeurIPS 2024 · similarity 0.92)
- MRCN: A Novel Modality Restitution and Compensation Network for Visible-Infrared Person Re-identification (AAAI 2023 · similarity 0.92)
- Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.91)
- Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.89)
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.
