Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unsupervised Multi-Source Domain Adaptation for 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 |
|---|---|---|---|
| Add RDSBN and MDIF to MMT | MMT · Duke→Market | mAP: 74.6 -> 81.5 | Helped |
| Add RDSBN and MDIF to MMT | MMT · Market→Duke | mAP: 61.0 -> 66.6 | Helped |
| Use RDSBN instead of DSBN (ablation) | ResNet50 · Duke+CUHK→Market | mAP: 74.1 -> 78.2 | Helped |
| Add MDIF (ablation) | ResNet50-RDSBN · Duke+CUHK→Market | mAP: 78.2 -> 79.4 | Helped |
| Replace direct instance graph with a weighted mean domain-agent-node (ablation) | MDIF · Duke+CUHK→Market | mAP: 72.4 -> 73.2 | Helped |
| Use a weighted mean agent node instead of a simple mean agent node (ablation) | MDIF · Duke+CUHK→Market | mAP: 72.9 -> 73.2 | Helped |
| Add intra-connections in the first GCN layer (ablation) | MDIF · Duke+CUHK→Market | mAP: 73.2 -> 73.1 | Hurt |
| Use RDSBN instead of DSBN (ablation) | ResNet50 · Market+CUHK→Duke | mAP: 60.4 -> 63.5 | Helped |
| Add MDIF (ablation) | ResNet50-RDSBN · Market+CUHK→Duke | mAP: 63.5 -> 65.0 | Helped |
| Add intra-connections in the first GCN layer (ablation) | MDIF · Market+CUHK→Duke | mAP: 62.7 -> 61.9 | Hurt |
| Use more source domains for direct transfer (ablation) | Direct Transfer · Market1501 target | mAP: 27.7 -> 36.0 -> 40.3 | Helped |
| Add source data during MMT fine-tuning (ablation) | MMT · Market1501 target | mAP: 74.6 -> 68.9; 75.3 -> 75.3; 74.8 -> 77.7 | Mixed |
Closest papers by meaning
- Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification (ICLR 2020 · similarity 0.92)
- Domain Adaptive Attention Learning for Unsupervised Person Re-Identification (AAAI 2020 · similarity 0.92)
- Image-Image Domain Adaptation With Preserved Self-Similarity and Domain-Dissimilarity for Person Re-Identification (CVPR 2018 · similarity 0.91)
- Unsupervised Domain Adaptation for Person Re-identification via Heterogeneous Graph Alignment (AAAI 2021 · similarity 0.91)
- Divide-and-Regroup Clustering for Domain Adaptive Person Re-identification (AAAI 2022 · similarity 0.90)
- Reliability Exploration with Self-Ensemble Learning for Domain Adaptive Person Re-identification (AAAI 2022 · 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.