Research map / Label-efficient and robust learning / Knowledge distillation
One-Shot Knowledge Transfer for Scalable Person Re-Identification
Longhua Li, Lei Qi, Xin Geng
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 |
|---|---|---|---|
| use trained teacher weights instead of a randomly initialized teacher (ablation) | OSKT Res-50-S1 · Market1501 single scenario (ablation) | mAP: 54.7 -> 75.7 | Improved |
| use trained teacher weights instead of a randomly initialized teacher (ablation) | OSKT ViT-S-S1 · Market1501 single scenario (ablation) | mAP: 33.0 -> 74.2 | Improved |
| initialize the weight chain with cluster centers instead of random clustering (ablation) | OSKT Res-50-S1 · Market1501 single scenario (ablation) | mAP: 55.1 -> 75.7 | Improved |
| initialize with clustering instead of inverse clustering (ablation) | OSKT Res-50-S1 · Market1501 single scenario (ablation) | mAP: 46.1 -> 75.7 | Improved |
| use Euclidean distance for ResNet and cosine for ViT rather than swapped (ablation) | OSKT ViT-S-S1 · Market1501 single scenario (ablation) | mAP: 64.9 -> 74.2 | Improved |
| use Euclidean distance for ResNet rather than cosine (ablation) | OSKT Res-50-S1 · Market1501 single scenario (ablation) | mAP: 74.2 -> 75.7 | No clear effect |
| add progressive refinement of the weight chain (ablation) | OSKT Res-50-S1 · Market1501 single scenario (ablation) | mAP: 52.2 -> 75.7 | Improved |
| add progressive refinement of the weight chain (ablation) | OSKT ViT-S-S1 · Market1501 single scenario (ablation) | mAP: 56.6 -> 74.2 | Improved |
| train teacher loss L_T jointly during refinement (ablation) | OSKT Res-50-S1 · Market1501 single scenario (ablation) | mAP: 62.7 -> 75.7 | Improved |
| use the default alpha schedule for L_ref instead of swapped (ablation) | OSKT Res-50-S1 · Market1501 single scenario (ablation) | mAP: 75.6 -> 75.7 | No clear effect |
| OSKT instead of DepGraph pruning for Res-50-S1 | student generation · Market1501 single scenario (ResNet50 teacher) | mAP: 61.3 -> 75.7 | Improved |
| OSKT initialization instead of ImageNet-free pretrain on OSNet width 0.25 | OSNet 0.25 · CUHK03 (pretrained on MSMT17) | mAP: 58.0 -> 60.6 | Improved |
Closest papers by meaning
- Long Short-Term Knowledge Decomposition and Consolidation for Lifelong Person Re-Identification (TPAMI 2025 · similarity 0.86)
- DKC: Differentiated Knowledge Consolidation for Cloth-Hybrid Lifelong Person Re-identification (CVPR 2025 · similarity 0.86)
- Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification (CVPR 2024 · similarity 0.85)
- LSTKC: Long Short-Term Knowledge Consolidation for Lifelong Person Re-identification (AAAI 2024 · similarity 0.85)
- Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions (CVPR 2024 · similarity 0.85)
- DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification (AAAI 2025 · 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.
