Research map / Label-efficient and robust learning / Domain adaptation and generalization
SECRET: Self-Consistent Pseudo Label Refinement for Unsupervised 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 |
|---|---|---|---|
| add mutual refinement of independently clustered global and local pseudo labels (ablation) | SECRET · Duke-to-Market | mAP: 72.4 -> 79.8 | Helped |
| use naive concatenated-feature clustering instead of mutual refinement (ablation) | SECRET · Duke-to-Market | mAP: 79.8 -> 71.5 | Hurt |
| add mutual refinement with both top and bottom local feature spaces (ablation) | SECRET · Duke-to-Market | mAP: 75.4 -> 79.8; 74.8 -> 79.8 | Helped |
| add mean teacher training (ablation) | SECRET-Joint · Market-to-MSMT | mAP: 25.4 -> 31.7 | Helped |
| use global and local features jointly at inference instead of only global (ablation) | SECRET · Market-to-Duke | mAP: 67.1 -> 68.2 | Helped |
| use only the top local feature at inference instead of the global feature (ablation) | SECRET · Duke-to-Market | mAP: 79.8 -> 65.6 | Hurt |
| use only the bottom local feature at inference instead of the global feature (ablation) | SECRET · Duke-to-Market | mAP: 79.8 -> 68.2 | Hurt |
Closest papers by meaning
- Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification (ICLR 2020 · similarity 0.93)
- Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification (AAAI 2021 · similarity 0.91)
- Reliability Exploration with Self-Ensemble Learning for Domain Adaptive Person Re-identification (AAAI 2022 · similarity 0.91)
- Group-aware Label Transfer for Domain Adaptive Person Re-identification (CVPR 2021 · similarity 0.91)
- Delving into Probabilistic Uncertainty for Unsupervised Domain Adaptive Person Re-identification (AAAI 2022 · similarity 0.91)
- Domain Adaptive Attention Learning for Unsupervised Person Re-Identification (AAAI 2020 · similarity 0.90)
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.