Research map / Label-efficient and robust learning / Recognition and long-tail
Generalized Relevance Learning Grassmann Quantization
Mohammad Mohammadi, Mohammad Babai, Michael H. F. Wilkinson
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 |
|---|---|---|---|
| use GRLGQ subspace prototypes instead of GTLVQ | GLVQ classifiers · MNIST | accuracy: 94.50 -> 94.78 | Improved |
| use GRLGQ instead of GTLVQ | GLVQ classifiers · Yale Face Database | accuracy: 94.64 -> 96.50 | Improved |
| use GRLGQ instead of GGPLCR | image-set classifier · Ex. Yale B | accuracy: 88.57 -> 90.12 | Improved |
| use GRLGQ instead of GGPLCR | image-set classifier · ETH-80 | accuracy: 96.75 -> 94.5 | Hurt |
| use GRLGQ instead of AMLSL | image-set classifier · UCF Sports | accuracy: 74.00 -> 80.00 | Improved |
| add relevance factors over principal angles (ablation) | GRLGQ · ETH-80 | accuracy vs subspace dimension: other methods drop below 90% when d exceeds 3 | Improved |
| increase subspace dimensionality with relevance factors (ablation) | GRLGQ · Ex. Yale B | accuracy | No clear effect |
| use prototype strategy instead of storing training subspaces | GRLGQ vs G(G)PLCR · ETH-80 parameter count | number of parameters: 60000 -> 16,005 | Improved |
| use GRLGQ instead of G(G)PLCR | parameter count · Ex. Yale B | number of parameters: 134400 -> 280000 | Hurt |
Closest papers by meaning
- Approximate Grassmannian Intersections: Subspace-Valued Subspace Learning (ICCV 2017 · similarity 0.87)
- Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class Representation (ICCV 2023 · similarity 0.84)
- Building Deep Networks on Grassmann Manifolds (AAAI 2018 · similarity 0.83)
- Random features for Grassmannian kernel approximation with bounded rank-one projections (NeurIPS 2026 · similarity 0.83)
- Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methods (TPAMI 2017 · similarity 0.83)
- StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold (NeurIPS 2025 · similarity 0.81)
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.
