Research map / Label-efficient and robust learning / Domain adaptation and generalization
IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID
Yongxing Dai, Jun Liu, Yifan Sun, Zekun Tong, Chi Zhang, Ling-Yu Duan
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 prediction-space bridge loss (ablation) | IDM on Strong Baseline · Market->Duke | mAP: 67.3 -> 70.5 | Improved |
| add feature-space bridge loss (ablation) | IDM on Strong Baseline · Market->Duke | mAP: 69.0 -> 70.5 | Improved |
| add diversity loss (ablation) | IDM on Strong Baseline · Market->Duke | mAP: 67.8 -> 70.5 | Improved |
| add prediction-space bridge loss (ablation) | IDM on Naive Baseline · Market->Duke | mAP: 66.2 -> 68.6 | Improved |
| add feature-space bridge loss (ablation) | IDM on Naive Baseline · Market->Duke | mAP: 65.8 -> 68.6 | Improved |
| add diversity loss (ablation) | IDM on Naive Baseline · Market->Duke | mAP: 64.8 -> 68.6 | Improved |
| add IDM module | Strong Baseline · Market->Duke | mAP: 65.8 -> 70.5 | Improved |
| add IDM module | Naive Baseline · Market->Duke | mAP: 63.4 -> 68.6 | Improved |
| add XBM memory bank for hard negatives | Naive Baseline · Market->Duke | mAP: 63.4 -> 65.8 | Improved |
| plug IDM after stage-0 instead of stage-4 (ablation) | IDM on Strong Baseline · Market->Duke | mAP: 68.4 -> 70.5 | Improved |
| use IBN-ResNet-50 instead of ResNet-50 | IDM · Market->MSMT17 | mAP: 33.5 -> 39.3 | Improved |
| use IBN-ResNet-50 instead of ResNet-50 | IDM · Duke->Market | mAP: 82.8 -> 83.9 | Improved |
Closest papers by meaning
- Bridging the Source-to-Target Gap for Cross-Domain Person Re-identification with Intermediate Domains (IJCV 2024 · similarity 0.94)
- Unsupervised Multi-Source Domain Adaptation for Person Re-Identification (CVPR 2021 · similarity 0.92)
- Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification (ICCV 2019 · similarity 0.91)
- Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification (ECCV 2020 · similarity 0.91)
- Unsupervised Domain Adaptive Person Search via Dual Self-Calibration (AAAI 2025 · similarity 0.89)
- Mixture of Submodules for Domain Adaptive Person Search (CVPR 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.
