Research map / Label-efficient and robust learning / Domain adaptation and generalization
Part-Aware Transformer for Generalizable Person Re-identification
Hao Ni, Yuke Li, Lianli Gao, Heng Tao Shen, Jingkuan Song
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 conventional self-distillation to the baseline (ablation) | TransReID-B/16 baseline · Market1501 -> DukeMTMC | mAP: 46.5 -> 44.9 | Hurt |
| add Cross-ID Similarity Learning (CSL) (ablation) | TransReID-B/16 baseline · Market1501 -> DukeMTMC | mAP: 46.5 -> 48.3 | Improved |
| add Part-guided Self-Distillation on top of CSL (ablation) | PAT · Market1501 -> MSMT17 | Rank-1: 40.2 -> 42.8 | Improved |
| add CSL+PSD to DeiT-Tiny backbone | DeiT-Tiny · Market1501 -> DukeMTMC | Rank-1: 39.0 -> 48.5 | Improved |
| add CSL+PSD to ViT-Base backbone | ViT-Base · Market1501 -> DukeMTMC | mAP: 46.5 -> 48.9 | Improved |
| use 3 parts instead of 2 (ablation) | PAT · Market1501 -> DukeMTMC | mAP: 47.0 -> 48.9 | Improved |
| use 3 parts instead of 5 (ablation) | PAT · Market1501 -> DukeMTMC | mAP: 47.9 -> 48.9 | Improved |
| pure Transformer PAT vs prior SOTA on multi-source M+D+C to MSMT17 | PAT · M+D+C -> MSMT17 | mAP: 14.7 -> 21.6 | Improved |
| PAT vs TransMatcher on Market -> MSMT | PAT · Market1501 -> MSMT17 | Rank-1: 47.3 -> 42.8 | Hurt |
Closest papers by meaning
- Adaptive Cross-Domain Learning for Generalizable Person Re-identification (ECCV 2022 · similarity 0.91)
- Generalizable Person Re-Identification by Domain-Invariant Mapping Network (CVPR 2019 · similarity 0.91)
- Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification (ECCV 2022 · similarity 0.90)
- Dynamically Transformed Instance Normalization Network for Generalizable Person Re-identification (ECCV 2022 · similarity 0.90)
- DC-Former: Diverse and Compact Transformer for Person Re-identification (AAAI 2023 · similarity 0.90)
- Generalizable Person Re-identification via Balancing Alignment and Uniformity (NeurIPS 2024 · 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.
