Research map / Label-efficient and robust learning / Recognition and long-tail
Semantic-Aligned Learning with Collaborative Refinement for Unsupervised VI-ReID
De Cheng, Lingfeng He, Nannan Wang, Dingwen Zhang, Xinbo Gao
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 dual association (DAGL) to the DCL baseline (ablation) | DCL baseline · SYSU-MM01 All-Search (single-shot) | mAP: 39.65 -> 53.87 | Improved |
| add FGSAL to DAGL (ablation) | SALCR · SYSU-MM01 All-Search (single-shot) | mAP: 53.87 -> 57.21 | Improved |
| add GPCR to DAGL+FGSAL (ablation) | SALCR · SYSU-MM01 All-Search (single-shot) | mAP: 57.21 -> 58.64 | Improved |
| add GPCR to DAGL only (ablation) | SALCR · SYSU-MM01 All-Search (single-shot) | mAP: 53.87 -> 55.61 | Improved |
| add CMFP(tr) to the full SALCR during training (ablation) | SALCR · SYSU-MM01 All-Search (single-shot) | mAP: 58.64 -> 60.44 | Improved |
| add CMFP(tr) to SALCR on RegDB (ablation) | SALCR · RegDB Visible-to-Infrared | mAP: 83.23 -> 83.87 | No clear effect |
| use dual association instead of visible-only association (ablation) | DAGL · SYSU-MM01 All-Search (single-shot) | mAP: 47.61 -> 53.87 | Improved |
| use dual association instead of infrared-only association (ablation) | DAGL · SYSU-MM01 All-Search (single-shot) | mAP: 51.90 -> 53.87 | Improved |
| add global loss only in GPCR (ablation) | SALCR · SYSU-MM01 All-Search (single-shot) | mAP: 58.48 -> 59.71 | Improved |
| add both global and part losses in GPCR (ablation) | SALCR · SYSU-MM01 All-Search (single-shot) | mAP: 58.48 -> 60.44 | Improved |
| apply CMFP re-ranking at test time | SALCR · SYSU-MM01 All-Search (single-shot) | mAP: 60.44 -> 74.08 | Improved |
| apply CMFP at test time versus CMRR (k=15) | SALCR · SYSU-MM01 All-Search (single-shot) | mAP: 69.14 -> 74.08 | Improved |
Closest papers by meaning
- Exploring Homogeneous and Heterogeneous Consistent Label Associations for Unsupervised Visible-Infrared Person ReID (IJCV 2024 · similarity 0.93)
- Syncretic Modality Collaborative Learning for Visible Infrared Person Re-Identification (ICCV 2021 · similarity 0.92)
- Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.92)
- Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.91)
- Empowering Visible-Infrared Person Re-Identification with Large Foundation Models (NeurIPS 2024 · similarity 0.91)
- TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification (AAAI 2025 · 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.
