Research map / Label-efficient and robust learning / Domain adaptation and generalization
Divide-and-Regroup Clustering for Domain Adaptive 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 |
|---|---|---|---|
| Apply DARC clustering to IDM | IDM · MSMT → Market | mAP: 82.1 -> 85.1 | Helped |
| Apply DARC clustering to IDM | IDM · Market → MSMT | top-1: 61.3 -> 64.5 | Helped |
| Apply DARC clustering to IDM | IDM · PersonX → Market | mAP: 81.3 -> 83.1 | Helped |
| Apply DARC clustering to IDM | IDM · PersonX → MSMT17 | mAP: 30.3 -> 32.3 | Helped |
| Apply DARC clustering to IDM | IDM · Unreal → Market | mAP: 83.2 -> 85.1 | Helped |
| Apply DARC clustering to IDM | IDM · Unreal → MSMT17 | mAP: 38.3 -> 39.1 | Helped |
| Add temporal distance to local clustering (ablation) | DARC with SPCL · PersonX → Market | mAP: 77.4 -> 78.9 | Helped |
| Add temporal distance to local clustering (ablation) | DARC with SPCL · MSMT → Market | mAP: 79.4 -> 80.9 | Helped |
| Use soft sample weighting during training (ablation) | DARC with SPCL · PersonX → Market | mAP: 77.6 -> 78.9 | Helped |
| Use soft sample weighting during training (ablation) | DARC with SPCL · MSMT → Market | mAP: 79.7 -> 80.9 | Helped |
| Use camera-specific local clustering and vote-to-regroup | SPCL · PersonX → Market | mAP: 73.8 -> 78.9 | Helped |
Closest papers by meaning
- AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification (CVPR 2020 · similarity 0.91)
- Asymmetric Co-Teaching for Unsupervised Cross-Domain Person Re-Identification (AAAI 2020 · similarity 0.91)
- Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification (ICLR 2020 · similarity 0.91)
- Unsupervised Multi-Source Domain Adaptation for Person Re-Identification (CVPR 2021 · similarity 0.90)
- Unsupervised Domain Adaptive Person Search via Dual Self-Calibration (AAAI 2025 · similarity 0.89)
- Exploring the Camera Bias of Person Re-identification (ICLR 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.