Research map / Label-efficient and robust learning / Domain adaptation and generalization
Multiple Expert Brainstorming for Domain Adaptive Person Re-identification
Yunpeng Zhai, Qixiang Ye, Shijian Lu, Mengxi Jia, Rongrong Ji, Yonghong Tian
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 temporally average models for soft labels (ablation) | MEB-Net · Market->DukeMTMC-reID (UDA) | mAP: 58.3 -> 66.1 | Improved |
| add temporally average models for soft labels (ablation) | MEB-Net · Duke->Market-1501 (UDA) | mAP: 70.7 -> 76.0 | Improved |
| add mutual identity loss (ablation) | MEB-Net · Duke->Market-1501 (UDA) | mAP: 70.2 -> 76.0 | Improved |
| add mutual identity loss (ablation) | MEB-Net · Market->DukeMTMC-reID (UDA) | mAP: 60.4 -> 66.1 | Improved |
| add mutual triplet loss (ablation) | MEB-Net · Duke->Market-1501 (UDA) | mAP: 74.9 -> 76.0 | Improved |
| add mutual triplet loss (ablation) | MEB-Net · Market->DukeMTMC-reID (UDA) | mAP: 63.0 -> 66.1 | Improved |
| add authority regularization (ablation) | MEB-Net · Duke->Market-1501 (UDA) | mAP: 75.5 -> 76.0 | Improved |
| add authority regularization (ablation) | MEB-Net · Market->DukeMTMC-reID (UDA) | mAP: 65.4 -> 66.1 | Improved |
| add authority regularization (ablation) | MEB-Net · Market->DukeMTMC-reID (UDA) | Rank-1: 77.9 -> 79.6 | Improved |
| add authority regularization (ablation) | MEB-Net · Market->DukeMTMC-reID (UDA) | Rank-5: 88.9 -> 88.3 | Hurt |
| add mutual learning losses and temporal averaging on top of voting-loss baseline (ablation) | MEB-Net · Duke->Market-1501 (UDA) | mAP: 69.5 -> 76.0 | Improved |
| add mutual learning losses and temporal averaging on top of voting-loss baseline (ablation) | MEB-Net · Market->DukeMTMC-reID (UDA) | mAP: 60.6 -> 66.1 | Improved |
Closest papers by meaning
- Unsupervised Multi-Source Domain Adaptation for Person Re-Identification (CVPR 2021 · similarity 0.88)
- Reliability Exploration with Self-Ensemble Learning for Domain Adaptive Person Re-identification (AAAI 2022 · similarity 0.88)
- Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification (ECCV 2020 · similarity 0.88)
- IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID (ICCV 2021 · similarity 0.87)
- Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-Identification (CVPR 2019 · similarity 0.87)
- Self-Training With Progressive Augmentation for Unsupervised Cross-Domain Person Re-Identification (ICCV 2019 · similarity 0.87)
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.
