Research map / Label-efficient and robust learning / Recognition and long-tail
Analysis-Synthesis Dictionary Learning for Universality-Particularity Representation Based Classification
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 |
|---|---|---|---|
| add universality representation and Fisher-like regularization (ASDL-UP vs DPL) | DPL (analysis-synthesis dictionary pair) · UCF Sports action | accuracy (%): 92.9 -> 95.0 | Helped |
| add universality representation (ASDL-UP vs DPL) | DPL (analysis-synthesis dictionary pair) · UCF50 action | accuracy (%): 62.4 -> 62.8 | Helped |
| add universality representation (ASDL-UP vs DPL) | DPL (analysis-synthesis dictionary pair) · AR face recognition | accuracy (%): 98.3 -> 99.5 | Helped |
| add universality representation (ASDL-UP vs DPL) | DPL (analysis-synthesis dictionary pair) · LFWa face recognition | accuracy (%): 74.6 -> 78.1 | Helped |
| add universality representation (ASDL-UP vs DPL) | DPL (analysis-synthesis dictionary pair) · LFW gender classification | accuracy (%): 92.0 -> 93.1 | Helped |
Closest papers by meaning
- Coupled Dictionary Learning for Unsupervised Feature Selection (AAAI 2016 · similarity 0.85)
- Personalized Dictionary Learning for Heterogeneous Datasets (NeurIPS 2023 · similarity 0.84)
- Discriminative Semi-Supervised Dictionary Learning with Entropy Regularization for Pattern Classification (AAAI 2017 · similarity 0.84)
- Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning (NeurIPS 2024 · similarity 0.80)
- On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning (NeurIPS 2026 · similarity 0.80)
- Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models (ICML 2025 · similarity 0.80)
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.