Research map / Label-efficient and robust learning / Recognition and long-tail
Bilevel Distance Metric Learning for Robust Image Recognition
Read the paperCheck 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 |
|---|---|---|---|
| learn sparse-coding features jointly with the metric (bilevel) instead of LMNN on fixed features | LMNN · NUST-RF indoor | accuracy (%): 36.20 ± 3.30 -> 47.84 ± 1.18 | Helped |
| bilevel model instead of LMNN | LMNN · NUST-RF outdoor | accuracy (%): 46.01 ± 2.06 -> 58.21 ± 1.68 | Helped |
| bilevel model instead of FANTOPE | FANTOPE · NUST-RF outdoor | accuracy (%): 58.72 ± 1.33 -> 58.21 ± 1.68 | No clear effect |
| bilevel model instead of LMNN | LMNN · OSR original (clean) | accuracy (%): 74.41 -> 74.43 ± 1.14 | No clear effect |
| bilevel model instead of LMNN | LMNN · OSR regular occlusion | accuracy (%): 58.66 -> 64.77 ± 1.46 | Helped |
| bilevel model instead of LMNN | LMNN · OSR irregular occlusion | accuracy (%): 57.02 ± 1.80 -> 62.72 ± 3.06 | Helped |
| bilevel model instead of LMNN | LMNN · OSR sparse noise | accuracy (%): 66.67 ± 1.70 -> 68.72 ± 2.72 | Helped |
| bilevel model instead of LMNN | LMNN · PubFig regular occlusion | accuracy (%): 37.48 ± 1.64 -> 44.29 ± 0.54 | Helped |
| bilevel model instead of LMNN | LMNN · PubFig irregular occlusion | accuracy (%): 41.73 ± 3.39 -> 49.10 ± 1.09 | Helped |
| bilevel model instead of LMNN | LMNN · PubFig original (clean) | accuracy (%): 61.65 ± 1.63 -> 63.46 ± 1.65 | Helped |
| add low-rank regularization on M (FANTOPE/CAP) to LMNN | LMNN · OSR and PubFig occluded data | accuracy (%) | No clear effect |
Closest papers by meaning
- Large-Scale Distance Metric Learning With Uncertainty (CVPR 2018 · similarity 0.87)
- Revisiting Metric Learning for SPD Matrix Based Visual Representation (CVPR 2017 · similarity 0.86)
- Matrix Variate Gaussian Mixture Distribution Steered Robust Metric Learning (AAAI 2018 · similarity 0.86)
- Metric Learning as Convex Combinations of Local Models With Generalization Guarantees (CVPR 2016 · similarity 0.85)
- Robust Metric Learning on Grassmann Manifolds with Generalization Guarantees (AAAI 2019 · similarity 0.85)
- Learning Low-Dimensional Metrics (NeurIPS 2017 · 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.