Research map / Label-efficient and robust learning / Domain adaptation and generalization
AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification
Check 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 |
|---|---|---|---|
| Add density-based clustering to direct source-to-target transfer (ablation) | ResNet-50 re-ID model · DukeMTMC-reID → Market-1501 | R-1: 46.3 to 73.8 | Helped |
| Add density-based clustering to direct source-to-target transfer (ablation) | ResNet-50 re-ID model · Market-1501 → DukeMTMC-reID | R-1: 28.0 to 68.6 | Helped |
| Add adaptive sample augmentation (ablation) | Density-based clustering baseline · DukeMTMC-reID → Market-1501 | R-1: 73.8 to 83.3 | Helped |
| Add adaptive sample augmentation (ablation) | Density-based clustering baseline · DukeMTMC-reID → Market-1501 | mAP: 51.0 to 62.8 | Helped |
| Add adaptive sample augmentation (ablation) | Density-based clustering baseline · Market-1501 → DukeMTMC-reID | R-1: 68.6 to 71.5 | Helped |
| Add adaptive sample augmentation (ablation) | Density-based clustering baseline · Market-1501 → DukeMTMC-reID | mAP: 49.0 to 52.7 | Helped |
| Add discriminative learning with min-max optimization (ablation) | Baseline+ASA · DukeMTMC-reID → Market-1501 | R-1: 83.3 to 86.7 | Helped |
| Add discriminative learning with min-max optimization (ablation) | Baseline+ASA · DukeMTMC-reID → Market-1501 | mAP: 62.8 to 68.3 | Helped |
| Add discriminative learning with min-max optimization (ablation) | Baseline+ASA · Market-1501 → DukeMTMC-reID | R-1: 71.5 to 72.6 | Helped |
| Add discriminative learning with min-max optimization (ablation) | Baseline+ASA · Market-1501 → DukeMTMC-reID | mAP: 52.7 to 54.1 | Helped |
| Use AD-Cluster instead of UDAP | Unsupervised person re-ID · DukeMTMC-reID → Market-1501 | mAP: 53.7 to 68.3 | Helped |
| Use AD-Cluster instead of UDAP | Unsupervised person re-ID · Market-1501 → DukeMTMC-reID | mAP: 49.0 to 54.1 | Helped |
Closest papers by meaning
- Divide-and-Regroup Clustering for Domain Adaptive Person Re-identification (AAAI 2022 · similarity 0.91)
- A Bottom-Up Clustering Approach to Unsupervised Person Re-Identification (AAAI 2019 · similarity 0.90)
- Asymmetric Co-Teaching for Unsupervised Cross-Domain Person Re-Identification (AAAI 2020 · similarity 0.90)
- Reliability Exploration with Self-Ensemble Learning for Domain Adaptive Person Re-identification (AAAI 2022 · similarity 0.89)
- Group-aware Label Transfer for Domain Adaptive Person Re-identification (CVPR 2021 · similarity 0.89)
- Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-Identification (CVPR 2019 · 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.