Research map / Label-efficient and robust learning / Recognition and long-tail
DLME: Deep Local-Flatness Manifold Embedding
Zelin Zang, Siyuan Li, Di Wu, Ge Wang, Kai Wang, Lei Shang, Baigui Sun, Hao Li, Stan Z. Li
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 |
|---|---|---|---|
| use DLME instead of UMAP for 2D embedding | linear SVM · EMnist | classification accuracy: 0.588 -> 0.657 | Improved |
| use DLME instead of best CL baseline | SimCLR-style linear test · TinyImageNet | linear-test accuracy: 0.388 -> 0.449 | Improved |
| use DLME instead of CC for deep clustering | CC · TinyImageNet | clustering accuracy: 0.140 -> 0.182 | Improved |
| use DLME instead of CRLC for deep clustering | CRLC · CIFAR10 | clustering accuracy: 0.799 -> 0.822 | Improved |
| add LD gradient on structure network f (versus CL loss on f) (ablation) | DLME · CIFAR10 clustering | clustering accuracy: 0.792 -> 0.822 | Improved |
| add t-distribution kernel (versus standard kernel) (ablation) | DLME-A1 · TinyImageNet clustering | clustering accuracy: 0.145 -> 0.133 | Mixed |
| add two-network structure (versus single-network CL) (ablation) | DLME-A2 · CIFAR10 linear test | linear-test accuracy: 0.888 -> 0.902 | Improved |
| add data augmentation-based CL framework with LD loss (ablation) | DLME-A3 · CIFAR100 linear test | linear-test accuracy: 0.624 -> 0.661 | Improved |
| use DLME vs tSNE on KMnist classification | linear SVM · KMnist | classification accuracy: 0.738 -> 0.782 | Improved |
| use DLME on HCL vs tSNE | linear SVM · HCL | classification accuracy: 0.874 -> 0.874 | No clear effect |
Closest papers by meaning
- ManifoldNet: A Deep Neural Network for Manifold-Valued Data With Applications (TPAMI 2020 · similarity 0.88)
- No Pressure! Addressing the Problem of Local Minima in Manifold Learning Algorithms (NeurIPS 2019 · similarity 0.87)
- Efficient Representation of Low-Dimensional Manifolds using Deep Networks (ICLR 2017 · similarity 0.87)
- Representation Learning via Manifold Flattening and Reconstruction (JMLR 2024 · similarity 0.87)
- Curvature Enhanced Data Augmentation for Regression (ICML 2025 · similarity 0.85)
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · similarity 0.85)
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.
