Research map / Label-efficient and robust learning / Recognition and long-tail
Salience-Guided Cascaded Suppression 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 |
|---|---|---|---|
| Use cascaded salience suppression with SFE stages | SCSN · CUHK03 labeled | mAP: 76.90 -> 84.00 | Helped |
| Use cascaded salience suppression with SFE stages | SCSN · CUHK03 detected | mAP: 74.80 -> 81.00 | Helped |
| Add CAM to the baseline (ablation) | DukeMTMC-ReID baseline · DukeMTMC-ReID | mAP: 71.50 -> 73.80 | Helped |
| Add SAM without residual update to the baseline (ablation) | DukeMTMC-ReID baseline · DukeMTMC-ReID | mAP: 71.50 -> 73.50 | Helped |
| Add RSAM to the baseline (ablation) | DukeMTMC-ReID baseline · DukeMTMC-ReID | mAP: 71.50 -> 74.10 | Helped |
| Combine CAM and SAM (ablation) | DukeMTMC-ReID baseline · DukeMTMC-ReID | mAP: 71.50 -> 75.80 | Helped |
| Use RDAM (CAM + RSAM) (ablation) | DukeMTMC-ReID baseline · DukeMTMC-ReID | mAP: 71.50 -> 76.20 | Helped |
| Add one SFE stage with B&A (ablation) | DukeMTMC-ReID · DukeMTMC-ReID | mAP: 76.20 -> 78.30 | Helped |
| Use two instead of one SFE stage with B&A (ablation) | DukeMTMC-ReID · DukeMTMC-ReID | mAP: 78.30 -> 78.80 | Helped |
| Increase SFE stages from two to three (ablation) | DukeMTMC-ReID · DukeMTMC-ReID | mAP: 78.80 -> 78.50 | Hurt |
| Add NMFF to B&A + two SFE stages (ablation) | DukeMTMC-ReID · DukeMTMC-ReID | mAP: 78.80 -> 79.00 | Helped |
| Fuse early and late backbone features using NMFF (ablation) | DukeMTMC-ReID baseline B · DukeMTMC-ReID | mAP: 78.50 -> 78.60 | Helped |
Closest papers by meaning
- Harmonious Attention Network for Person Re-Identification (CVPR 2018 · similarity 0.87)
- Person30K: A Dual-Meta Generalization Network for Person Re-Identification (CVPR 2021 · similarity 0.87)
- From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization (CVPR 2025 · similarity 0.87)
- Prototype-Guided Saliency Feature Learning for Person Search (CVPR 2021 · similarity 0.87)
- Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.86)
- Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification (AAAI 2024 · 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.