Research map / Label-efficient and robust learning / Domain adaptation and generalization
Invariance Matters: Exemplar Memory for Domain Adaptive 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 exemplar-invariance (ablation) | Source-only re-ID model · DukeMTMC-reID → Market-1501 | Rank-1: 43.1 -> 48.7 | Helped |
| add camera-invariance to exemplar-invariance (ablation) | Exemplar-invariance model · DukeMTMC-reID → Market-1501 | Rank-1: 48.7 -> 63.1 | Helped |
| add neighborhood-invariance to exemplar-invariance (ablation) | Exemplar-invariance model · Market-1501 → DukeMTMC-reID | Rank-1: 34.2 -> 39.7 | Helped |
| add neighborhood-invariance to exemplar- and camera-invariance (ablation) | Ours w/ E+C · DukeMTMC-reID → Market-1501 | Rank-1: 63.1 -> 75.1 | Helped |
| use exemplar memory instead of mini-batch relationships (ablation) | Invariance learning system · DukeMTMC-reID → Market-1501 | Rank-1: 67.2 -> 75.1 | Helped |
| vary temperature β (ablation) | ECN · DukeMTMC-reID → Market-1501 | Rank-1: 47.3; 72.3; 75.1; 71.4; 52.3; 47.8 | Mixed |
| vary temperature β (ablation) | ECN · Market-1501 → DukeMTMC-reID | Rank-1: 29.1; 59.7; 63.3; 59.3; 45.4; 40.2 | Mixed |
| vary target-loss weight λ from source-only training to including target invariance learning (ablation) | ECN · Target-domain re-ID | Rank-1 accuracy and mAP | Helped |
| vary the number k of candidate positive samples (ablation) | Neighborhood-invariance learning · Target-domain re-ID | Rank-1 accuracy and mAP | Mixed |
Closest papers by meaning
- Domain Adaptive Attention Learning for Unsupervised Person Re-Identification (AAAI 2020 · similarity 0.90)
- Reliability Exploration with Self-Ensemble Learning for Domain Adaptive Person Re-identification (AAAI 2022 · similarity 0.90)
- Unsupervised Multi-Source Domain Adaptation for Person Re-Identification (CVPR 2021 · similarity 0.90)
- Mixture of Submodules for Domain Adaptive Person Search (CVPR 2025 · similarity 0.88)
- Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic (ICLR 2024 · similarity 0.87)
- Exploring the Camera Bias of Person Re-identification (ICLR 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.