Research map / Label-efficient and robust learning / Recognition and long-tail
Euler Sparse Representation for Image Classification
Yang Liu, Quanxue Gao, Jungong Han, Shujian Wang
Read the paperCheck 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 |
|---|---|---|---|
| replace pixel-space SRC with Euler SRC (Euler representation) | SRC · AR Exp.2 (PCA) | classification accuracy (%): 77.74±1.12 -> 83.63±0.83 | Improved |
| replace pixel-space SRC with Euler SRC (Euler representation) | SRC · AR Exp.1 (PCA) | classification accuracy (%): 80.00±0.49 -> 82.98±0.42 | Improved |
| replace pixel-space SRC with Euler SRC (Euler representation) | SRC · LFWCrop (PCA) | classification accuracy (%): 50.40±3.04 -> 55.13±2.86 | Improved |
| replace pixel-space SRC with Euler SRC (Euler representation) | SRC · COIL20 (PCA) | classification accuracy (%): 98.71±0.77 -> 99.28±0.50 | Improved |
| replace pixel-space SRC with Euler SRC (Euler representation) | SRC · AR Exp.2 (down-sampling) | classification accuracy (%): 75.90±0.19 -> 77.25±0.29 | Improved |
| replace pixel-space SRC with Euler SRC (Euler representation) | SRC · LFWCrop (down-sampling) | classification accuracy (%): 51.03±2.10 -> 52.20±1.86 | No clear effect |
| vary Euler parameter gamma from 0 to 2 (best at 1.9) (ablation) | Euler SRC · COIL20 | classification accuracy (%) | No clear effect |
Closest papers by meaning
- Adaptive Class Preserving Representation for Image Classification (CVPR 2017 · similarity 0.84)
- Discriminant Projection Representation-Based Classification for Vision Recognition (AAAI 2018 · similarity 0.83)
- Sparse Representation-Based Open Set Recognition (TPAMI 2016 · similarity 0.83)
- Convolutional Dictionary Learning via Local Processing (ICCV 2017 · similarity 0.83)
- SparseFormer: Sparse Visual Recognition via Limited Latent Tokens (ICLR 2024 · similarity 0.82)
- I-Con: A Unifying Framework for Representation Learning (ICLR 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.
