Research map / Label-efficient and robust learning / Recognition and long-tail
Viewpoint-Aware Loss with Angular Regularization for 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 viewpoint-aware adaptive label smoothing (ablation) | VA-reID with adaptive identity label smoothing · Market-1501 | mAP: 86.97 -> 88.67 | Helped |
| add viewpoint-aware adaptive label smoothing (ablation) | VA-reID with adaptive identity label smoothing · DukeMTMC-reID | mAP: 77.99 -> 78.86 | Helped |
| add center regularization (ablation) | VA-reID with adaptive identity label smoothing · Market-1501 | mAP: 86.97 -> 88.25 | Helped |
| add center regularization (ablation) | VA-reID with adaptive identity label smoothing · DukeMTMC-reID | mAP: 77.99 -> 78.25 | Helped |
| replace fixed label smoothing with adaptive identity label smoothing (ablation) | identity classification · Market-1501 | mAP: 86.72 -> 86.97 | Helped |
| replace fixed label smoothing with adaptive identity label smoothing (ablation) | identity classification · DukeMTMC-reID | mAP: 77.47 -> 77.99 | Helped |
| add local multi-stripe features (ablation) | VA-reID · Market-1501 | mAP: 89.97 -> 91.70 | Helped |
| add local multi-stripe features (ablation) | VA-reID · DukeMTMC-reID | mAP: 81.48 -> 84.51 | Helped |
| add reranking (ablation) | VA-reID · Market-1501 | mAP: 91.70 -> 95.43 | Helped |
| use predicted viewpoints instead of ground-truth viewpoints (ablation) | VA-reID · DukeMTMC-reID | mAP: 81.48 -> 81.05 | No clear effect |
| use pose-clustered viewpoints instead of ground-truth viewpoints (ablation) | VA-reID · DukeMTMC-reID | mAP: 81.48 -> 80.69 | No clear effect |
Closest papers by meaning
- Exploring the Camera Bias of Person Re-identification (ICLR 2025 · similarity 0.88)
- Camera-Aware Proxies for Unsupervised Person Re-Identification (AAAI 2021 · similarity 0.87)
- Unleashing Potential of Unsupervised Pre-Training With Intra-Identity Regularization for Person Re-Identification (CVPR 2022 · similarity 0.86)
- Dissecting Person Re-Identification From the Viewpoint of Viewpoint (CVPR 2019 · similarity 0.86)
- From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization (CVPR 2025 · similarity 0.86)
- Semantics-Aligned Representation Learning for Person Re-Identification (AAAI 2020 · similarity 0.86)
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.