Research map / Label-efficient and robust learning / Domain adaptation and generalization
Asymmetric Co-Teaching for Unsupervised Cross-Domain 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 asymmetric co-teaching that selects clean inliers for the collaborator and diverse outliers for the main model (ablation) | Theory-based adaptation · DukeMTMC-reID → Market-1501 | mAP: 52.0 -> 60.6 | Helped |
| Add asymmetric co-teaching that selects clean inliers for the collaborator and diverse outliers for the main model (ablation) | Theory-based adaptation · Market-1501 → DukeMTMC-reID | mAP: 48.4 -> 54.5 | Helped |
| Add nearest-neighbor-labeled outliers to Theory training (ablation) | Theory · DukeMTMC-reID → Market-1501 | mAP: 52.0 -> 54.7 | Helped |
| Add nearest-neighbor-labeled outliers to Theory training (ablation) | Theory · Market-1501 → DukeMTMC-reID | mAP: 48.4 -> 49.1 | Helped |
| Use symmetric co-teaching to filter noisy samples (ablation) | Theory adaptation · DukeMTMC-reID → Market-1501 | mAP: 52.0 -> 55.0 | Helped |
| Use symmetric co-teaching to filter noisy samples (ablation) | Theory adaptation · Market-1501 → DukeMTMC-reID | mAP: 48.4 -> 47.3 | Hurt |
| Add outliers to symmetric co-teaching (ablation) | CT · Market-1501 → DukeMTMC-reID | mAP: 47.3 -> 49.6 | Helped |
| Add outliers to symmetric co-teaching (ablation) | CT · DukeMTMC-reID → Market-1501 | mAP: 55.0 -> 55.3 | No clear effect |
| Use asymmetric rather than symmetric co-teaching with outliers (ablation) | CT with outliers · DukeMTMC-reID → Market-1501 | mAP: 55.3 -> 60.6 | Helped |
| Use asymmetric rather than symmetric co-teaching with outliers (ablation) | CT with outliers · Market-1501 → DukeMTMC-reID | mAP: 49.6 -> 54.5 | Helped |
| Apply ACT with k-means, marking the furthest 20% samples as outliers (ablation) | k-means-based adaptation · DukeMTMC-reID → Market-1501 | mAP: 52.7 -> 56.0 | Helped |
| Apply ACT with k-means, marking the furthest 20% samples as outliers (ablation) | k-means-based adaptation · Market-1501 → DukeMTMC-reID | mAP: 46.7 -> 49.8 | Helped |
Closest papers by meaning
- Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification (ICLR 2020 · similarity 0.91)
- A Bottom-Up Clustering Approach to Unsupervised Person Re-Identification (AAAI 2019 · similarity 0.91)
- Camera-Aware Proxies for Unsupervised Person Re-Identification (AAAI 2021 · similarity 0.91)
- Divide-and-Regroup Clustering for Domain Adaptive Person Re-identification (AAAI 2022 · similarity 0.91)
- Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification (CVPR 2021 · similarity 0.90)
- Unsupervised Person Re-Identification by Soft Multilabel Learning (CVPR 2019 · 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.