Research map / Label-efficient and robust learning / Recognition and long-tail
Unsupervised Cross-Dataset Transfer Learning for 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 |
|---|---|---|---|
| transfer knowledge from four labelled source datasets using UMDL rather than training the single-task variant | UMDL · VIPeR | Rank-1 matching accuracy (%): 24.3 -> 31.5 | Helped |
| transfer knowledge from four labelled source datasets using UMDL rather than training the single-task variant | UMDL · PRID | Rank-1 matching accuracy (%): 14.1 -> 24.2 | Helped |
| transfer knowledge from four labelled source datasets using UMDL rather than training the single-task variant | UMDL · CUHK01 | Rank-1 matching accuracy (%): 13.8 -> 27.1 | Helped |
| transfer knowledge from four labelled source datasets using UMDL rather than training the single-task variant | UMDL · CAVIAR | Rank-1 matching accuracy (%): 33.5 -> 41.6 | Helped |
| transfer knowledge from four labelled source datasets using UMDL rather than training the single-task variant | UMDL · iLIDS | Rank-1 matching accuracy (%): 45.7 -> 49.3 | Helped |
| add the target-unique view-invariant dictionary Du_T (ablation) | UMDL · VIPeR | Rank-1 matching accuracy (%): 27.2 -> 31.5 | Helped |
| add the target-unique view-invariant dictionary Du_T (ablation) | UMDL · PRID | Rank-1 matching accuracy (%): 22.3 -> 24.2 | Helped |
| add the target-unique view-invariant dictionary Du_T (ablation) | UMDL · CUHK01 | Rank-1 matching accuracy (%): 24.5 -> 27.1 | Helped |
| add the target-unique view-invariant dictionary Du_T (ablation) | UMDL · CAVIAR | Rank-1 matching accuracy (%): 38.1 -> 41.6 | Helped |
| add the target-unique view-invariant dictionary Du_T (ablation) | UMDL · iLIDS | Rank-1 matching accuracy (%): 46.5 -> 49.3 | Helped |
| use stepwise reconstruction error terms (ablation) | UMDL · VIPeR | Rank-1 matching accuracy (%): 23.8 -> 31.5 | Helped |
| use stepwise reconstruction error terms (ablation) | UMDL · PRID | Rank-1 matching accuracy (%): 18.9 -> 24.2 | Helped |
Closest papers by meaning
- Unsupervised Cross-Dataset Person Re-Identification by Transfer Learning of Spatial-Temporal Patterns (CVPR 2018 · similarity 0.91)
- Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification (CVPR 2018 · similarity 0.90)
- Domain Adaptive Attention Learning for Unsupervised Person Re-Identification (AAAI 2020 · similarity 0.90)
- Unsupervised Pre-Training for Person Re-Identification (CVPR 2021 · similarity 0.90)
- Unsupervised Person Re-Identification by Soft Multilabel Learning (CVPR 2019 · similarity 0.90)
- Joint Discriminative and Generative Learning for Person Re-Identification (CVPR 2019 · similarity 0.89)
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.