Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Constrained Dominant Sets for Person Re-Identification
Leulseged Tesfaye Alemu, Marcello Pelillo, Mubarak Shah
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 the constrained dominant sets (CDS) branch (ablation) | baseline verification network (SD) · Market1501 | mAP: 72.2 -> 81.4 | Improved |
| add the constrained dominant sets (CDS) branch (ablation) | baseline verification network (SD) · Market1501 | rank-1: 86.5 -> 93.3 | Improved |
| add the constrained dominant sets (CDS) branch (ablation) | baseline verification network (SD) · DukeMTMC-reID | mAP: 61.1 -> 69.1 | Improved |
| add the auxiliary multi-scale net (ablation) | DCDS (SD) · Market1501 | mAP: 81.4 -> 83.0 | Improved |
| add the auxiliary multi-scale net (ablation) | DCDS (SD) · DukeMTMC-reID | mAP: 69.1 -> 74.4 | Improved |
| add the auxiliary multi-scale net (ablation) | DCDS (SD) · CUHK03 | rank-1: 93.1 -> 95.4 | Improved |
| pretrain on the merged multi-dataset (MD) instead of a single dataset (ablation) | DCDS · Market1501 | mAP: 81.4 -> 82.3 | Improved |
| pretrain on the merged multi-dataset (MD) instead of a single dataset (ablation) | baseline · Market1501 | mAP: 72.2 -> 74.3 | Improved |
| add re-ranking as post-processing | Ours · Market1501 | mAP: 85.8 -> 93.3 | Improved |
| add re-ranking as post-processing | Ours · DukeMTMC-reID | mAP: 75.5 -> 86.1 | Improved |
| increase the fusing parameter beta (ablation) | DCDS · Market1501 | mAP | Improved |
| increase images per person-ID Omega from 4 to 16 (ablation) | DCDS · Market1501 | mAP | No clear effect |
Closest papers by meaning
- Resource Aware Person Re-Identification Across Multiple Resolutions (CVPR 2018 · similarity 0.90)
- Deep Neural Networks with Inexact Matching for Person Re-Identification (NeurIPS 2016 · similarity 0.90)
- A Bottom-Up Clustering Approach to Unsupervised Person Re-Identification (AAAI 2019 · similarity 0.90)
- A Pose-Sensitive Embedding for Person Re-Identification With Expanded Cross Neighborhood Re-Ranking (CVPR 2018 · similarity 0.89)
- Multi-Scale Deep Learning Architectures for Person Re-Identification (ICCV 2017 · similarity 0.89)
- Cheb-GR: Rethinking K-nearest Neighbor Search in Re-ranking for Person Re-identification (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.
