Research map / Label-efficient and robust learning / Recognition and long-tail
Faster Person Re-Identification
Guan’an Wang, Shaogang Gong, Jian Cheng, Zengguang Hou
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 code pyramid (CP) structure (ablation) | AiO binary codes · Market-1501 (32-bit code) | Rank-1: 25.5 -> 54.4 | Improved |
| add code pyramid (CP) structure (ablation) | AiO with CtF search · Market-1501 | mAP: 75.1 -> 80.2 | Improved |
| add self-distillation (SD) on top of CP (ablation) | AiO binary codes · Market-1501 (32-bit code) | Rank-1: 54.4 -> 60.0 | Improved |
| add self-distillation (SD) on top of CP (ablation) | AiO with CtF search · Market-1501 | mAP: 80.2 -> 84.0 | Improved |
| add CP and SD together (ablation) | AiO binary codes · Market-1501 (32-bit code) | Rank-1: 25.5 -> 60.0 | Improved |
| add CP and SD together (ablation) | AiO binary codes · Market-1501 (2048-bit code) | Rank-1: 93.8 -> 93.8 | No clear effect |
| use real-value instead of binary 32-d features | AiO · Market-1501 (32-d) | Rank-1: 25.5 -> 82.7 | Improved |
| use real-value instead of binary 2048-d features | AiO · Market-1501 (2048-d) | Rank-1: 93.8 -> 94.2 | No clear effect |
| lengthen binary code from 512 to 2048 bits | ABC hashing · Market-1501 | Rank-1: 69.4 -> 81.4 | Improved |
| lengthen binary code from 32 to 2048 bits | AiO · Market-1501 | Rank-1: 60.0 -> 93.7 | Improved |
| use coarse-to-fine search instead of 2048-bit only | AiO · Market-1501 | query time (s): 2.8x10^-1 -> 4.6x10^-2 | Improved |
| use coarse-to-fine search instead of 2048-bit only | AiO · DukeMTMC-reID | Rank-1: 87.7 -> 87.6 | No clear effect |
Closest papers by meaning
- Faster Person Re-Identification: One-Shot-Filter and Coarse-to-Fine Search (TPAMI 2023 · similarity 0.96)
- Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-Identification (TPAMI 2025 · similarity 0.88)
- Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions (CVPR 2024 · similarity 0.87)
- Person Re-Identification by Discriminative Selection in Video Ranking (TPAMI 2016 · similarity 0.87)
- Global Distance-distributions Separation for Unsupervised Person Re-identification (ECCV 2020 · similarity 0.87)
- Cheb-GR: Rethinking K-nearest Neighbor Search in Re-ranking for Person Re-identification (CVPR 2025 · 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.
