Research map / Label-efficient and robust learning / Recognition and long-tail
Coupled Dictionary Learning for Unsupervised Feature Selection
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 |
|---|---|---|---|
| use L2,p-norm with p=0.8 instead of L2,1 (p=1.0) (ablation) | CDL-FS · COIL20 | classification accuracy (%): 88.45 -> 92.15 | Helped |
| use L2,p-norm with p=0.8 instead of L2,1 (p=1.0) (ablation) | CDL-FS · USPS | classification accuracy (%): 91.74 -> 92.79 | Helped |
| use L2,p-norm with p=0.8 instead of L2,1 (p=1.0) (ablation) | CDL-FS · ISOLET | classification accuracy (%): 76.75 -> 76.97 | Helped |
| use L2,p-norm with p=0.8 instead of L2,1 (p=1.0) (ablation) | CDL-FS · warpAR10P | classification accuracy (%): 90.92 -> 89.37 | Hurt |
| use L2,p-norm with p=0.8 instead of L2,1 (p=1.0) (ablation) | CDL-FS · warpAR10P | clustering NMI (%): 48.26 -> 42.05 | Hurt |
| use L2,p-norm with p=0.8 instead of L2,1 (p=1.0) (ablation) | CDL-FS · COIL20 | clustering NMI (%): 68.02 -> 71.42 | Helped |
| use L2,p-norm p in (0,1) instead of L2,1 across datasets (ablation) | CDL-FS · six datasets | accuracy and NMI | Mixed |
| use very small p=0.4 instead of 0.8 (ablation) | CDL-FS · warpAR10P | clustering NMI (%): 42.05 -> 39.22 | Hurt |
| coupled dictionary learning (CDL-FS p=0.8) instead of matrix-factorization method RUFS | unsupervised feature selection · COIL20 | classification accuracy (%): 90.18 -> 92.15 | Helped |
| coupled dictionary learning (CDL-FS p=0.8) instead of RUFS | unsupervised feature selection · USPS | classification accuracy (%): 92.11 -> 92.79 | Helped |
Closest papers by meaning
- Dependence Guided Unsupervised Feature Selection (AAAI 2018 · similarity 0.85)
- Analysis-Synthesis Dictionary Learning for Universality-Particularity Representation Based Classification (AAAI 2016 · similarity 0.85)
- Unsupervised Feature Selection Through Group Discovery (AAAI 2026 · similarity 0.85)
- Consensus Guided Unsupervised Feature Selection (AAAI 2016 · similarity 0.84)
- Dictionary Learning in Optimal Metric Space (AAAI 2018 · similarity 0.83)
- Unsupervised Feature Selection with Structured Graph Optimization (AAAI 2016 · similarity 0.83)
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.