Research map / Label-efficient and robust learning / Domain adaptation and generalization
Generalizable Person Re-Identification by Domain-Invariant Mapping Network
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 DIMN rather than PPA | person re-identification · VIPeR | rank-1: 45.06% -> 51.23% | Helped |
| Use DIMN rather than the strongest listed aggregation baseline | person re-identification · PRID | rank-1: 38.90% -> 39.20% | Helped |
| Use DIMN rather than the strongest listed aggregation baseline | person re-identification · GRID | rank-1: 36.00% -> 29.28% | Hurt |
| Use DIMN rather than the strongest listed aggregation baseline | person re-identification · i-LIDS | rank-1: 69.17% -> 70.17% | Helped |
| Add a memory bank (ablation) | DIMN · VIPeR, PRID, GRID, and i-LIDS | rank-1: 45.44% -> 51.23%; 37.10% -> 39.20%; 30.08% -> 29.28%; 69.00% -> 70.17% | Mixed |
| Use running-average rather than direct memory rewriting (ablation) | DIMN · VIPeR, PRID, GRID, and i-LIDS | rank-1: 50.03% -> 51.23%; 36.50% -> 39.20%; 30.48% -> 29.28%; 67.67% -> 70.17% | Mixed |
| Add logit-triplet loss (ablation) | DIMN · VIPeR, PRID, GRID, and i-LIDS | rank-1: 49.53% -> 51.23%; 37.90% -> 39.20%; 32.88% -> 29.28%; 65.50% -> 70.17% | Mixed |
| Use DIMN rather than PPA | MiniImageNet few-shot classification · MiniImageNet 5-way 1-shot | accuracy: 49.64±0.58% -> 50.74±0.54% | Helped |
| Use DIMN rather than MAML | MiniImageNet few-shot classification · MiniImageNet 5-way 5-shot | accuracy: 63.11±0.92% -> 63.13±0.42% | No clear effect |
Closest papers by meaning
- Person30K: A Dual-Meta Generalization Network for Person Re-Identification (CVPR 2021 · similarity 0.93)
- Style Normalization and Restitution for Generalizable Person Re-Identification (CVPR 2020 · similarity 0.91)
- Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification (CVPR 2021 · similarity 0.90)
- Exploring the Camera Bias of Person Re-identification (ICLR 2025 · similarity 0.90)
- Generalizable Person Re-identification via Balancing Alignment and Uniformity (NeurIPS 2024 · 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.