Research map / Label-efficient and robust learning / Recognition and long-tail
Efficient Deep Embedded Subspace Clustering
Check 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 the reconstruction loss (ablation) | EDESC · STL-10 | ACC: 0.512 -> 0.745 | Helped |
| Add the reconstruction loss (ablation) | EDESC · REUTERS-10K | ACC: 0.727 -> 0.825 | Helped |
| Add the subspace clustering loss (ablation) | EDESC · STL-10 | ACC: 0.626 -> 0.745 | Helped |
| Add the subspace clustering loss (ablation) | EDESC · REUTERS-10K | ACC: 0.662 -> 0.825 | Helped |
| Add the subspace proxy constraint (ablation) | EDESC · STL-10 | ACC: 0.550 -> 0.745 | Helped |
| Add the subspace proxy constraint (ablation) | EDESC · REUTERS-10K | ACC: 0.799 -> 0.825 | Helped |
| Use a very low clustering-loss weight β (ablation) | EDESC · REUTERS-10K | NMI | Hurt |
| Use an excessive clustering-loss weight β (ablation) | EDESC · REUTERS-10K | NMI | Hurt |
| Vary the subspace dimension d (ablation) | EDESC · REUTERS-10K | NMI | Mixed |
Closest papers by meaning
- Deep Subspace Clustering Networks (NeurIPS 2017 · similarity 0.94)
- Exploring a Principled Framework for Deep Subspace Clustering (ICLR 2025 · similarity 0.94)
- LRSC: Learning Representations for Subspace Clustering (AAAI 2021 · similarity 0.93)
- A Critique of Self-Expressive Deep Subspace Clustering (ICLR 2021 · similarity 0.93)
- Unsupervised Deep Embedding for Clustering Analysis (ICML 2016 · similarity 0.91)
- You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering (NeurIPS 2025 · similarity 0.86)
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.