Research map / Learning theory and algorithms / Prediction and decision losses
Metric Learning as Convex Combinations of Local Models With Generalization Guarantees
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 C2LM instead of Perrot et al.'s method | Perceptual color distance estimation · Unseen colors | test loss | Helped |
| Use C2LM instead of Perrot et al.'s method | Perceptual color distance estimation · Unseen cameras | test loss | Helped |
| Use C2LM instead of cosine similarity | Word embedding semantic similarity · WordSim353-similarity | test loss | Helped |
| Use C2LM instead of a global bilinear form | Word embedding semantic similarity · WordSim353-similarity | test loss | Helped |
| Use local bilinear forms instead of a global bilinear form | Word embedding semantic similarity · WordSim353-similarity | test loss | No clear effect |
| Increase the number of clusters from one to two (ablation) | C2LM · WordSim353-similarity | test loss | Hurt |
| Increase the number of clusters (ablation) | C2LM · Perceptual color distance estimation | test loss | Helped |
Closest papers by meaning
- Divide and Conquer the Embedding Space for Metric Learning (CVPR 2019 · similarity 0.87)
- Large-Scale Distance Metric Learning With Uncertainty (CVPR 2018 · similarity 0.87)
- Curvilinear Distance Metric Learning (NeurIPS 2019 · similarity 0.87)
- Parameter Free Large Margin Nearest Neighbor for Distance Metric Learning (AAAI 2017 · similarity 0.87)
- Semi-Supervised Metric Learning: A Deep Resurrection (AAAI 2021 · similarity 0.86)
- Learning Low-Dimensional Metrics (NeurIPS 2017 · similarity 0.86)
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.