Research map / Image generation / Editing and style transfer
FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
Read the paperCheck 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 a Siamese verification model instead of a single-branch baseline | person re-identification model · Market-1501 | mAP: 59.8 -> 72.5 | Helped |
| Add the FD-GAN pose-guided generation and discriminator framework | Siamese baseline · Market-1501 | mAP: 72.5 -> 77.7 | Helped |
| Add online pose-map augmentation (ablation) | FD-GAN · Market-1501 | mAP: 77.2 -> 77.7 | Helped |
| Add the identity discriminator (ablation) | FD-GAN · Market-1501 | mAP: 72.8 -> 77.7 | Helped |
| Add the pose discriminator (ablation) | FD-GAN · Market-1501 | mAP: 73.0 -> 77.7 | Helped |
| Add both identity and pose discriminators (ablation) | FD-GAN · Market-1501 | mAP: 71.6 -> 77.7 | Helped |
| Add the same-pose loss (ablation) | FD-GAN · Market-1501 | mAP: 75.8 -> 77.7 | Helped |
| Add identity verification loss (ablation) | FD-GAN · Market-1501 | mAP: 75.7 -> 77.7 | Helped |
| Add both same-pose and identity verification losses (ablation) | FD-GAN · Market-1501 | mAP: 74.4 -> 77.7 | Helped |
| Do not share encoder weights between E and D_id (ablation) | FD-GAN · Market-1501 | mAP: 73.5 -> 77.7 | Helped |
| Add the FD-GAN framework | Siamese baseline · DukeMTMC-reID | mAP: 61.3 -> 64.5 | Helped |
| Add online pose-map augmentation (ablation) | FD-GAN · DukeMTMC-reID | mAP: 63.9 -> 64.5 | Helped |
Closest papers by meaning
- Learning Disentangled Representation for Robust Person Re-identification (NeurIPS 2019 · similarity 0.94)
- Pose Transferrable Person Re-Identification (CVPR 2018 · similarity 0.89)
- Joint Generative and Contrastive Learning for Unsupervised Person Re-Identification (CVPR 2021 · similarity 0.89)
- Adversarially Occluded Samples for Person Re-Identification (CVPR 2018 · similarity 0.88)
- Person Transfer GAN to Bridge Domain Gap for Person Re-Identification (CVPR 2018 · similarity 0.88)
- From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization (CVPR 2025 · 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.