Research map / Label-efficient and robust learning / Recognition and long-tail
Mixed High-Order Attention Network for Person Re-Identification
Binghui Chen, Weihong Deng, Jiani Hu
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 six HOA modules (MHN-6) | PCB · Market-1501 | Rank-1: 93.1 -> 95.1 | Improved |
| add six HOA modules (MHN-6) | IDE · Market-1501 | mAP: 73.9 -> 83.6 | Improved |
| add six HOA modules (MHN-6) | PCB · CUHK03-NP Labeled | Rank-1: 61.9 -> 77.2 | Improved |
| increase number of HOA modules from 2 to 6 (ablation) | PCB · CUHK03-NP Labeled | Rank-1: 71.2 -> 77.2 | Improved |
| increase number of HOA modules from 2 to 6 (ablation) | IDE · Market-1501 | Rank-1: 90.6 -> 93.6 | Improved |
| add random erasing to PCB (ablation) | PCB · CUHK03-NP Labeled | Rank-1: 61.9 -> 57.4 | Hurt |
| add random erasing to IDE (ablation) | IDE · CUHK03-NP Labeled | Rank-1: 52.9 -> 61.4 | Improved |
| add adversary constraint L_adv (ablation) | MHN-6 (IDE) · Market-1501 | mAP: 80.0 -> 83.6 | Improved |
| add adversary constraint L_adv (ablation) | MHN-6 (PCB) · DukeMTMC-ReID | Rank-1: 87.7 -> 89.1 | Improved |
| add nonlinearity to HOA modules (ablation) | MHN-6 (PCB) · Market-1501 | mAP: 84.5 -> 85.0 | Improved |
| add nonlinearity to HOA modules (ablation) | MHN-6 (IDE) · Market-1501 | Rank-1: 93.3 -> 93.6 | Improved |
| place HOA modules after layer2 instead of layer1 (ablation) | MHN-6 (IDE) · Market-1501 | Rank-1: 92.2 -> 93.6 | Improved |
Closest papers by meaning
- Attention-Aware Compositional Network for Person Re-Identification (CVPR 2018 · similarity 0.89)
- Relation-Aware Global Attention for Person Re-Identification (CVPR 2020 · similarity 0.89)
- Self-Critical Attention Learning for Person Re-Identification (ICCV 2019 · similarity 0.89)
- Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions (CVPR 2024 · similarity 0.87)
- High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-identification (AAAI 2024 · similarity 0.87)
- 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.
