Research map / Label-efficient and robust learning / Domain adaptation and generalization
Instance-Guided Context Rendering for Cross-Domain Person Re-Identification
Yanbei Chen, Xiatian Zhu, Shaogang Gong
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 dual condition on target instances (ablation) | CR-GAN · Market1501 -> DukeMTMCreID | Rank-1: 43.3 -> 52.2 | Improved |
| add dual condition on target instances (ablation) | CR-GAN · DukeMTMCreID -> Market1501 | Rank-1: 55.5 -> 59.6 | Improved |
| add dual condition on target instances, with LMP (ablation) | CR-GAN+LMP · Market1501 -> DukeMTMCreID | Rank-1: 48.7 -> 56.0 | Improved |
| add dual condition on target instances, with LMP (ablation) | CR-GAN+LMP · DukeMTMCreID -> Market1501 | Rank-1: 59.2 -> 64.5 | Improved |
| add dual condition on target instances (ablation) | CR-GAN · Market->Duke image quality | LPIPS diversity: 0.196 -> 0.281 | Improved |
| add identity loss (ablation) | CR-GAN · Market1501 -> DukeMTMCreID | Rank-1: 31.9 -> 52.2 | Improved |
| add camera loss (ablation) | CR-GAN · Market1501 -> DukeMTMCreID | Rank-1: 48.8 -> 52.2 | Improved |
| add context loss (ablation) | CR-GAN · Market1501 -> DukeMTMCreID | Rank-1: 48.5 -> 52.2 | Improved |
| add context loss (ablation) | CR-GAN · DukeMTMCreID -> Market1501 | Rank-1: 57.4 -> 59.6 | Improved |
| add camera loss (ablation) | CR-GAN · DukeMTMCreID -> Market1501 | Rank-1: 53.6 -> 59.6 | Improved |
| add LMP pooling at test time | CR-GAN · Market1501 -> DukeMTMCreID | Rank-1: 52.2 -> 56.0 | Improved |
| combine CR-GAN synthetic pretraining with TAUDL | TAUDL · Market1501 -> DukeMTMCreID | Rank-1: 61.7 -> 68.9 | Improved |
Closest papers by meaning
- Image-Image Domain Adaptation With Preserved Self-Similarity and Domain-Dissimilarity for Person Re-Identification (CVPR 2018 · similarity 0.91)
- Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification (ECCV 2020 · similarity 0.90)
- Joint Generative and Contrastive Learning for Unsupervised Person Re-Identification (CVPR 2021 · similarity 0.90)
- Joint Discriminative and Generative Learning for Person Re-Identification (CVPR 2019 · similarity 0.90)
- Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification (ICCV 2019 · similarity 0.90)
- From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization (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.
