Research map / Label-efficient and robust learning / Recognition and long-tail
Interaction-And-Aggregation Network for Person Re-Identification
Check 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 the IA network blocks (SIA and CIA) to ResNet-50 | ResNet-50 · Market-1501 | mAP: 76.2 -> 83.1 | Helped |
| use multi-context SIA rather than a single-context patch (ablation) | SIA · Market-1501 | mAP: 79.0 -> 82.0 | Helped |
| fuse multi-context maps with element-wise product instead of maximum (ablation) | SIA · Market-1501 | mAP: 81.8 -> 82.0 | Helped |
| fuse multi-context maps with element-wise product instead of summation (ablation) | SIA · DukeMTMC-reID | top-1: 85.4 -> 85.6 | Helped |
| add location relations to appearance relations (ablation) | SIA · Market-1501 | mAP: 82.0 -> 82.5 | Helped |
| add CIA to the baseline (ablation) | ResNet-50 · Market-1501 | mAP: 76.2 -> 79.3 | Helped |
| use both SIA and CIA, with SIA before CIA (ablation) | ResNet-50 · Market-1501 | mAP: 79.3 -> 82.8 | Helped |
| place the IA block at stage 2 instead of stage 4 (ablation) | ResNet-50 · Market-1501 | mAP: 79.6 -> 82.8 | Helped |
| place IA blocks at bottlenecks instead of inside each stage 2/3 convolution block (ablation) | ResNet-50 · Market-1501 | mAP: 81.9 -> 83.1 | Helped |
| add IA blocks to ResNet32 (ablation) | ResNet32 · Market-1501 | mAP: 72.5 -> 79.2 | Helped |
Closest papers by meaning
- A Multi-Task Deep Network for Person Re-Identification (AAAI 2017 · similarity 0.90)
- Learning Deep Context-Aware Features Over Body and Latent Parts for Person Re-Identification (CVPR 2017 · similarity 0.90)
- Relation Network for Person Re-Identification (AAAI 2020 · similarity 0.90)
- Person30K: A Dual-Meta Generalization Network for Person Re-Identification (CVPR 2021 · similarity 0.90)
- Harmonious Attention Network for Person Re-Identification (CVPR 2018 · similarity 0.89)
- From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization (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.