Research map / Label-efficient and robust learning / Recognition and long-tail
Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised 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 |
|---|---|---|---|
| Use pseudo-labels for outliers in training (ablation) | Unsupervised re-ID framework · DukeMTMC-reID and Market-1501 | mAP: 6.8 -> 39.2; 6.6 -> 51.2 | Helped |
| Add DSCE loss (ablation) | Unsupervised re-ID with outliers · DukeMTMC-reID | mAP: 39.2 -> 43.4 | Helped |
| Add DSCE loss (ablation) | Unsupervised re-ID with outliers · Market-1501 | mAP: 51.2 -> 53.9 | Helped |
| Add MetaCam (ablation) | Unsupervised re-ID with outliers · DukeMTMC-reID | mAP: 39.2 -> 51.1 | Helped |
| Add MetaCam (ablation) | Unsupervised re-ID with outliers · Market-1501 | mAP: 51.2 -> 59.4 | Helped |
| Add MetaCam to training that uses DSCE (ablation) | Unsupervised re-ID with outliers and DSCE · DukeMTMC-reID | mAP: 43.4 -> 53.8 | Helped |
| Add MetaCam to training that uses DSCE (ablation) | Unsupervised re-ID with outliers and DSCE · Market-1501 | mAP: 53.9 -> 61.7 | Helped |
| Fine-tune MMT-500 with the proposed method | MMT-500 · Duke → Market | mAP: 71.2 -> 76.5 | Helped |
| Fine-tune MMT-500 with the proposed method | MMT-500 · Market → Duke | mAP: 63.1 -> 65.0 | Helped |
Closest papers by meaning
- Unsupervised Person Re-Identification via Softened Similarity Learning (CVPR 2020 · similarity 0.91)
- Camera-Aware Proxies for Unsupervised Person Re-Identification (AAAI 2021 · similarity 0.91)
- Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification (ICLR 2020 · similarity 0.91)
- Asymmetric Co-Teaching for Unsupervised Cross-Domain Person Re-Identification (AAAI 2020 · similarity 0.90)
- CDE-Learning: Camera Deviation Elimination Learning for Unsupervised Person Re-identification (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.