Research map / Label-efficient and robust learning / Domain adaptation and generalization
Group-aware Label Transfer 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 |
|---|---|---|---|
| use GLT rather than the strongest listed baseline | UDA person ReID · DukeMTMC→Market1501 | mAP: 76.0 -> 79.5 | Helped |
| use GLT rather than the strongest listed baseline | UDA person ReID · Market1501→DukeMTMC | mAP: 66.1 -> 69.2 | Helped |
| use GLT rather than the strongest listed baseline | UDA person ReID · Market1501→MSMT17 | mAP: 22.9 -> 26.5 | Helped |
| use GLT rather than the strongest listed baseline | UDA person ReID · DukeMTMC→MSMT17 | mAP: 23.3 -> 27.7 | Helped |
| add multi-group pseudo labels without label transfer (ablation) | Baseline · DukeMTMC→Market1501 | mAP: 59.5 -> 63.0 | Helped |
| add target instance memory bank (ablation) | Baseline · DukeMTMC→Market1501 | mAP: 59.5 -> 62.4 | Helped |
| add label transfer (ablation) | Baseline · DukeMTMC→Market1501 | mAP: 59.5 -> 66.4 | Helped |
| add target instance memory bank to label transfer (ablation) | Baseline + LT · DukeMTMC→Market1501 | mAP: 66.4 -> 68.2 | Helped |
| add group-aware label transfer (ablation) | Baseline + G · DukeMTMC→Market1501 | mAP: 63.0 -> 78.7 | Helped |
| add target instance memory bank to group-aware label transfer (ablation) | Baseline + G + GLT · DukeMTMC→Market1501 | mAP: 78.7 -> 79.5 | Helped |
| add triplet loss (ablation) | GLT · DukeMTMC→Market1501 | mAP: 77.3 -> 79.5 | Helped |
| add triplet loss (ablation) | GLT · Market1501→DukeMTMC | mAP: 67.1 -> 69.2 | Helped |
Closest papers by meaning
- Reliability Exploration with Self-Ensemble Learning for Domain Adaptive Person Re-identification (AAAI 2022 · similarity 0.93)
- Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification (AAAI 2021 · similarity 0.93)
- Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification (ICLR 2020 · similarity 0.93)
- Delving into Probabilistic Uncertainty for Unsupervised Domain Adaptive Person Re-identification (AAAI 2022 · similarity 0.92)
- SECRET: Self-Consistent Pseudo Label Refinement for Unsupervised Domain Adaptive Person Re-identification (AAAI 2022 · similarity 0.91)
- Unsupervised Group Re-identification via Adaptive Clustering-Driven Progressive Learning (AAAI 2024 · 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.