Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unsupervised Domain Adaptation with Noise Resistible Mutual-Training for Person Re-identification
Fang Zhao, Shengcai Liao, Guo-Sen Xie, Jian Zhao, Kaihao Zhang, Ling Shao
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 collaborative clustering (vs separate training) (ablation) | NRMT · DukeMTMC-reID -> Market-1501 | mAP: 54.2 -> 68.9 | Improved |
| add collaborative clustering (vs separate training) (ablation) | NRMT · Market-1501 -> DukeMTMC-reID | mAP: 48.7 -> 59.1 | Improved |
| add peer-confidence instance selection (ablation) | NRMT · DukeMTMC-reID -> Market-1501 | mAP: 68.9 -> 70.9 | Improved |
| add peer-confidence instance selection (ablation) | NRMT · Market-1501 -> DukeMTMC-reID | mAP: 59.1 -> 60.6 | Improved |
| add relationship-disagreement instance selection (ablation) | NRMT · DukeMTMC-reID -> Market-1501 | mAP: 70.9 -> 72.2 | Improved |
| add relationship-disagreement instance selection (ablation) | NRMT · Market-1501 -> DukeMTMC-reID | mAP: 60.6 -> 62.3 | Improved |
| adapt to target data with mutual training (vs direct transfer) (ablation) | NRMT · DukeMTMC-reID -> Market-1501 | mAP: 33.0 -> 72.2 | Improved |
| set peer-confidence threshold Tc=1.0 instead of 0 (ablation) | NRMT · Duke -> Market | mAP: 71.0 -> 72.2 | Improved |
| set Tc=1.0 instead of 2.0 (ablation) | NRMT · Duke -> Market | mAP: 71.7 -> 72.2 | Improved |
| set relationship-disagreement threshold Td=0.5 instead of 0.3 (ablation) | NRMT · Duke -> Market | mAP: 71.2 -> 72.2 | Improved |
| set Td=0.5 instead of 0.7 (ablation) | NRMT · Duke -> Market | mAP: 71.5 -> 72.2 | Improved |
| use 8 minimum samples in HDBSCAN instead of 6 (ablation) | NRMT · Duke -> Market | mAP: 71.5 -> 72.2 | Improved |
Closest papers by meaning
- 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)
- Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification (AAAI 2021 · similarity 0.90)
- Group-aware Label Transfer for Domain Adaptive Person Re-identification (CVPR 2021 · similarity 0.90)
- Reliability Exploration with Self-Ensemble Learning for Domain Adaptive Person Re-identification (AAAI 2022 · similarity 0.90)
- Unsupervised Domain Adaptive Person Search via Dual Self-Calibration (AAAI 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.
