Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Disentangled Representation 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 |
|---|---|---|---|
| Add identity shuffling with identity-related and identity-unrelated feature disentanglement (ablation) | Baseline reID model · Market-1501 | mAP (%): 84.1 -> 87.0 | Helped |
| Add identity shuffling with identity-related and identity-unrelated feature disentanglement (ablation) | Baseline reID model · CUHK03 labeled | rank-1 accuracy (%): 68.4 -> 73.4 | Helped |
| Add identity shuffling with identity-related and identity-unrelated feature disentanglement (ablation) | Baseline reID model · DukeMTMC-reID | mAP (%): 74.9 -> 79.5 | Helped |
| Add part-level identity shuffling (ablation) | IS-GAN with image-level shuffling · Market-1501 | mAP (%): 87.0 -> 87.1 | Helped |
| Add part-level identity shuffling (ablation) | IS-GAN with image-level shuffling · CUHK03 labeled | rank-1 accuracy (%): 73.4 -> 73.9 | Helped |
| Add part-level identity shuffling (ablation) | IS-GAN with image-level shuffling · DukeMTMC-reID | rank-1 accuracy (%): 89.5 -> 89.7 | Helped |
| Add the domain discriminator loss (ablation) | IS-GAN with part-level shuffling · DukeMTMC-reID | rank-1 accuracy (%): 89.7 -> 89.8 | Helped |
| Add the class discriminator loss (ablation) | IS-GAN with part-level shuffling · CUHK03 labeled | mAP (%): 72.1 -> 72.3 | Helped |
| Combine domain and class discriminator losses (ablation) | IS-GAN with part-level shuffling · CUHK03 labeled | rank-1 accuracy (%): 73.9 -> 74.1 | Helped |
| Add IS-GAN without part-level shuffling to PCB (ablation) | PCB · Market-1501 | mAP (%): 74.2 -> 78.3 | Helped |
| Add IS-GAN with part-level shuffling (ablation) | PCB · Market-1501 | mAP (%): 74.2 -> 78.5 | Helped |
| Increase the number of body-part branches from part-2 to part-3 (ablation) | IS-GAN with part-level shuffling · Market-1501 | rank-1 accuracy (%): 93.9 -> 94.4 | Helped |
Closest papers by meaning
- FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification (NeurIPS 2018 · similarity 0.94)
- Adversarially Occluded Samples for Person Re-Identification (CVPR 2018 · similarity 0.91)
- From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization (CVPR 2025 · similarity 0.90)
- DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID (CVPR 2025 · similarity 0.90)
- Exploring the Camera Bias of Person Re-identification (ICLR 2025 · similarity 0.88)
- Person De-reidentification: A Variation-guided Identity Shift Modeling (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.