Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Metric Learning via Facility Location
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 |
|---|---|---|---|
| Use structured facility-location clustering loss instead of N-pairs loss | Deep metric embedding · CUB200-2011 | NMI: 57.24 -> 59.23 | Helped |
| Use structured facility-location clustering loss instead of N-pairs loss | Deep metric embedding · Cars196 | R@1: 53.90 -> 58.11 | Helped |
| Use structured facility-location clustering loss instead of the strongest baseline | Deep metric embedding · Stanford Online Products | NMI: 89.46 -> 89.48 | Helped |
| Use structured facility-location clustering loss instead of the strongest baseline | Deep metric embedding · Stanford Online Products | R@1: 66.67 -> 67.02 | Helped |
| L2-normalize the embedding vectors (ablation) | Clustering (Ours) · Metric-learning experiments | performance | Helped |
| Initialize loss-augmented inference with the greedy solution rather than random initialization (ablation) | Clustering (Ours) · Loss-augmented inference | performance | Helped |
| Vary the unique-class-to-batch ratio among the tested settings (ablation) | Clustering (Ours) · CUB-200-2011 and Cars196 | experimental results | No clear effect |
Closest papers by meaning
- Divide and Conquer the Embedding Space for Metric Learning (CVPR 2019 · similarity 0.89)
- Signal-To-Noise Ratio: A Robust Distance Metric for Deep Metric Learning (CVPR 2019 · similarity 0.88)
- Deep Metric Learning via Lifted Structured Feature Embedding (CVPR 2016 · similarity 0.88)
- Local Similarity-Aware Deep Feature Embedding (NeurIPS 2016 · similarity 0.87)
- Deep Metric Learning Beyond Binary Supervision (CVPR 2019 · similarity 0.87)
- Ranked List Loss for Deep Metric Learning (CVPR 2019 · similarity 0.87)
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.