Research map / Label-efficient and robust learning / Recognition and long-tail
Adaptive Class Preserving Representation for Image Classification
Jian-Xun Mi, Qiankun Fu, Weisheng Li
Check your idea against 137,217 papers
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 adaptive class-preserving regularization instead of EN | image representation classification · GT (t=5) | accuracy: 67.44 -> 71.36 | Improved |
| Use adaptive class-preserving regularization instead of Lasso | image representation classification · GT (t=10) | accuracy: 77.20 -> 81.96 | Improved |
| Use adaptive class-preserving regularization instead of SGL | image representation classification · ORL (t=2) | accuracy: 85.84 -> 87.03 | Improved |
| Use adaptive class-preserving regularization instead of EN | image representation classification · ORL (t=6) | accuracy: 96.81 -> 97.56 | Improved |
| Use adaptive class-preserving regularization instead of Ridge | image representation classification · LFW11 | accuracy: 72.79 ± 0.86 -> 74.84 ± 1.04 | Improved |
| Use adaptive class-preserving regularization instead of GL | image representation classification · LFW16 | accuracy: 79.29 ± 2.05 -> 80.64 ± 1.57 | Improved |
| Use adaptive class-preserving regularization instead of GL | image representation classification · FERET (t=5) | accuracy: 66.75 -> 70.50 | Improved |
| Use adaptive class-preserving regularization instead of Lasso | image representation classification · MNIST | accuracy: 86.68 ± 2.00 -> 88.88 ± 1.65 | Improved |
| Use adaptive class-preserving regularization instead of Lasso | image representation classification · COIL20 | accuracy: 98.08 ± 0.55 -> 99.03 ± 0.60 | Improved |
Closest papers by meaning
- Sparse Coding for Classification via Discrimination Ensemble (CVPR 2016 · similarity 0.85)
- Uncorrelated Group LASSO (AAAI 2016 · similarity 0.85)
- Enhanced Group Sparse Regularized Nonconvex Regression for Face Recognition (TPAMI 2020 · similarity 0.85)
- Two-Layer Feature Reduction for Sparse-Group Lasso via Decomposition of Convex Sets (JMLR 2019 · similarity 0.85)
- Euler Sparse Representation for Image Classification (AAAI 2018 · similarity 0.84)
- Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation (ICML 2025 · similarity 0.84)
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.
