Research map / Label-efficient and robust learning / Recognition and long-tail
Weakly Supervised Discriminative Feature Learning With State Information for Person Identification
Hong-Xing Yu, Wei-Shi Zheng
Check 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 |
|---|---|---|---|
| Use hard WDBR and WFDR with state information | weakly supervised discriminative learning · DukeMTMC-reID | rank-1: 67.1 -> 72.1 | Improved |
| Use hard WDBR and WFDR with state information | weakly supervised discriminative learning · DukeMTMC-reID | mAP: 48.0 -> 53.8 | Improved |
| Use state-informed method rather than the strongest reported supervised baseline | weakly supervised discriminative learning · Multi-PIE | average recognition rate: 93.5 -> 97.1 | Improved |
| Use state-informed method rather than supervised fine-tuning | weakly supervised discriminative learning · CFP frontal-profile | Accuracy: 95.50(0.98) -> 95.49(0.70) | No clear effect |
| Add hard WDBR without WFDR (ablation) | Basic model · DukeMTMC-reID | rank-1: 56.8 -> 69.4 | Improved |
| Add WFDR without WDBR (ablation) | Basic model · DukeMTMC-reID | rank-1: 56.8 -> 67.7 | Improved |
| Add both WDBR and WFDR (ablation) | Basic model · DukeMTMC-reID | rank-1: 56.8 -> 72.1 | Improved |
| Add soft WDBR without WFDR (ablation) | Basic model · Multi-PIE | average recognition rate: 54.5 -> 97.0 | Improved |
| Add WFDR without WDBR (ablation) | Basic model · Multi-PIE | average recognition rate: 54.5 -> 95.7 | Improved |
| Add WFDR to soft-WDBR model (ablation) | Basic + WDBR (soft) · Multi-PIE | average recognition rate: 97.0 -> 97.1 | No clear effect |
| Use soft rather than hard WDBR (ablation) | Full model · Multi-PIE | average recognition rate: 95.7 -> 97.1 | Improved |
| Use soft rather than hard WDBR (ablation) | Full model · DukeMTMC-reID | rank-1: 70.3 -> 72.1 | Improved |
Closest papers by meaning
- Unsupervised Person Re-Identification by Soft Multilabel Learning (CVPR 2019 · similarity 0.89)
- Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identification (ICCV 2023 · similarity 0.88)
- Part-Based Pseudo Label Refinement for Unsupervised Person Re-Identification (CVPR 2022 · similarity 0.88)
- Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification (ICLR 2020 · similarity 0.88)
- Exploring the Camera Bias of Person Re-identification (ICLR 2025 · similarity 0.87)
- From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization (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.
