Research map / Label-efficient and robust learning / Recognition and long-tail
Efficient Online Local Metric Adaptation via Negative Samples for Person Re-Identification
Jiahuan Zhou, Pei Yu, Wei Tang, Ying Wu
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 OL-MANS online local metric adaptation (ablation) | Euclidean distance (LOMO) · VIPeR | Rank-1 accuracy: 15.32 -> 21.99 | Improved |
| add OL-MANS (ablation) | XQDA (LOMO) · VIPeR | Rank-1 accuracy: 38.99 -> 43.54 | Improved |
| add OL-MANS (ablation) | MLAPG (LOMO) · VIPeR | Rank-1 accuracy: 40.28 -> 44.97 | Improved |
| add OL-MANS (ablation) | DNSL (LOMO) · VIPeR | Rank-1 accuracy: 40.19 -> 43.67 | Improved |
| add OL-MANS (ablation) | Euclidean distance (LOMO) · GRID | Rank-1 accuracy: 9.12 -> 20.88 | Improved |
| add OL-MANS (ablation) | XQDA (LOMO) · GRID | Rank-1 accuracy: 12.96 -> 29.20 | Improved |
| add OL-MANS (ablation) | MLAPG (LOMO) · GRID | Rank-1 accuracy: 17.60 -> 30.16 | Improved |
| add OL-MANS (ablation) | DNSL (LOMO) · GRID | Rank-1 accuracy: 15.12 -> 28.96 | Improved |
| add OL-MANS (ablation) | MLAPG (LOMO) · Market-1501 (single-shot) | Rank-1 accuracy: 43.87 -> 44.93 | Improved |
| add OL-MANS | MLAPG (LOMO) · Market-1501 (multi-shot) | Rank-20 accuracy: 96.40 -> 94.27 | Hurt |
| add OL-MANS (ablation) | DNSL (LOMO) · Market-1501 (single-shot) | Rank-1 accuracy: 51.73 -> 60.67 | Improved |
| add OL-MANS (ablation) | XQDA (LOMO) · Market-1501 (multi-shot) | Rank-1 accuracy: 56.27 -> 74.00 | Improved |
Closest papers by meaning
- Online Joint Multi-Metric Adaptation From Frequent Sharing-Subset Mining for Person Re-Identification (CVPR 2020 · similarity 0.92)
- Embedding Deep Metric for Person Re-identification: A Study Against Large Variations (ECCV 2016 · similarity 0.90)
- Learning a Discriminative Null Space for Person Re-Identification (CVPR 2016 · similarity 0.90)
- Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification (ICCV 2017 · similarity 0.89)
- A Systematic Evaluation and Benchmark for Person Re-Identification: Features, Metrics, and Datasets (TPAMI 2018 · similarity 0.89)
- Hard-Aware Point-to-Set Deep Metric for Person Re-identification (ECCV 2018 · 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.
