Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Variational Metric Learning
Xudong Lin, Yueqi Duan, Qiyuan Dong, Jiwen Lu, Jie Zhou
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 DVML (variance disentangling and sample generation) | Triplet · Cars196 | Recall@1: 58.5 -> 64.3 | Improved |
| add DVML (variance disentangling and sample generation) | N-pair · Cars196 | Recall@1: 72.3 -> 80.4 | Improved |
| add DVML (variance disentangling and sample generation) | Triplet2+DWS · Cars196 | Recall@1: 78.9 -> 82.0 | Improved |
| add DVML (variance disentangling and sample generation) | Triplet · Stanford Online Products | Recall@1: 54.9 -> 66.5 | Improved |
| add DVML (variance disentangling and sample generation) | N-pair · Stanford Online Products | Recall@1: 66.4 -> 70.0 | Improved |
| add DVML (variance disentangling and sample generation) | Triplet2+DWS · Stanford Online Products | Recall@1: 66.8 -> 70.2 | Improved |
| add DVML (variance disentangling and sample generation) | Triplet · CUB-200-2011 | Recall@1: 39.8 -> 43.7 | Improved |
| add DVML (variance disentangling and sample generation) | N-pair · CUB-200-2011 | Recall@1: 50.6 -> 52.5 | Improved |
| add DVML (variance disentangling and sample generation) | Triplet2+DWS · CUB-200-2011 | Recall@1: 49.8 -> 52.7 | Improved |
| add DVML to N-pair | N-pair · Cars196 | NMI: 62.9 -> 66.0 | Improved |
| add DVML to Triplet | Triplet · Cars196 | F1: 21.3 -> 28.2 | Improved |
| add DVML to Triplet | Triplet · Stanford Online Products | F1: 20.2 -> 31.1 | Improved |
Closest papers by meaning
- Deep Disentangled Metric Learning (AAAI 2025 · similarity 0.89)
- Deep Compositional Metric Learning (CVPR 2021 · similarity 0.88)
- Revisiting Training Strategies and Generalization Performance in Deep Metric Learning (ICML 2020 · similarity 0.88)
- Distance Metric Learning with Joint Representation Diversification (ICML 2020 · similarity 0.88)
- Potential Field Based Deep Metric Learning (CVPR 2025 · similarity 0.85)
- Threshold-Consistent Margin Loss for Open-World Deep Metric Learning (ICLR 2024 · 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.
