Research map / Label-efficient and robust learning / Domain adaptation and generalization
Smoothing Adversarial Domain Attack and P-Memory Reconsolidation for Cross-Domain 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 LMP/LAP pooling (ablation) | Cross-domain re-ID baseline · DukeMTMC-reID→Market-1501 | rank-1: +6.7% | Helped |
| Add LMP/LAP pooling (ablation) | Cross-domain re-ID baseline · Market-1501→DukeMTMC-reID | rank-1: +18.8% | Helped |
| Add SADA image alignment (ablation) | LMP/LAP cross-domain re-ID · DukeMTMC-reID→Market-1501 | rank-1: +2.7% | Helped |
| Add SADA image alignment (ablation) | LMP/LAP cross-domain re-ID · Market-1501→DukeMTMC-reID | rank-1: +4.4% | Helped |
| Add p-memory reconsolidation (ablation) | LMP/LAP cross-domain re-ID · DukeMTMC-reID→Market-1501 | rank-1: +2.3% | Helped |
| Add p-memory reconsolidation (ablation) | LMP/LAP cross-domain re-ID · Market-1501→DukeMTMC-reID | rank-1: +2.6% | Helped |
| Combine SADA and pMR (ablation) | LMP/LAP cross-domain re-ID · DukeMTMC-reID→Market-1501 | rank-1: +4.9% | Helped |
| Combine SADA and pMR (ablation) | LMP/LAP cross-domain re-ID · Market-1501→DukeMTMC-reID | rank-1: +3.5% | Helped |
| Smooth attack gradients with a mean filter (ablation) | SADA · DukeMTMC-reID→Market-1501 | successful attack iterations: 39.4 -> 18.3 | Helped |
| Smooth attack gradients with a mean filter (ablation) | SADA · Market-1501→DukeMTMC-reID | successful attack iterations: 4.8 -> 1.9 | Helped |
| Set p to 0.3 for source-memory sampling (ablation) | pMR-SADA · Market-1501 and DukeMTMC-reID | rank-1 and mAP | Helped |
Closest papers by meaning
- Learning to Attack Real-World Models for Person Re-identification via Virtual-Guided Meta-Learning (AAAI 2021 · similarity 0.90)
- Image-Image Domain Adaptation With Preserved Self-Similarity and Domain-Dissimilarity for Person Re-Identification (CVPR 2018 · similarity 0.89)
- R$^2$TUA: Reconstruction-residual Based Targeted and Untargeted Attack Against Text-Image Person Re-Identification (CVPR 2026 · similarity 0.89)
- Feature-Level Adversarial Attacks and Ranking Disruption for Visible-Infrared Person Re-identification (NeurIPS 2024 · similarity 0.85)
- Noisy-Correspondence Learning for Text-to-Image Person Re-identification (CVPR 2024 · similarity 0.85)
- Generalizable Person Re-identification via Balancing Alignment and Uniformity (NeurIPS 2024 · similarity 0.85)
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.