Research map / Label-efficient and robust learning / Recognition and long-tail
Unsupervised Deep Embedding for Clustering Analysis
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 |
|---|---|---|---|
| jointly learn the embedding and cluster centers with DEC | DEC · MNIST | ACC: 53.49% -> 84.30% | Helped |
| jointly learn the embedding and cluster centers with DEC | DEC · STL-HOG | ACC: 28.39% -> 35.90% | Helped |
| jointly learn the embedding and cluster centers with DEC | DEC · REUTERS-10k | ACC: 52.42% -> 72.17% | Helped |
| jointly learn the embedding and cluster centers with DEC | DEC · REUTERS | ACC: 53.29% -> 75.63% | Helped |
| add end-to-end backpropagation during clustering (ablation) | DEC · STL-HOG | ACC: 34.06% -> 35.90% | Helped |
| add end-to-end backpropagation during clustering (ablation) | DEC · REUTERS-10k | ACC: 70.05% -> 72.17% | Helped |
| add end-to-end backpropagation during clustering (ablation) | DEC · REUTERS | ACC: 69.62% -> 75.63% | Helped |
| add autoencoder feature preprocessing before k-means | k-means · MNIST | ACC: 53.49% -> 81.84% | Helped |
| apply DEC after autoencoder and k-means initialization | DEC · MNIST imbalanced subsamples | ACC: 66.82% -> 70.10%; 74.91% -> 80.92%; 77.93% -> 82.68%; 80.04% -> 84.69%; 81.31% -> 85.41% | Helped |
| vary class retention from r_min=0.1 to r_min=0.9 | DEC · MNIST imbalanced subsamples | ACC: 70.10%; 80.92%; 82.68%; 84.69%; 85.41% | Mixed |
Closest papers by meaning
- Efficient Deep Embedded Subspace Clustering (CVPR 2022 · similarity 0.91)
- Deep Embedded Non-Redundant Clustering (AAAI 2020 · similarity 0.89)
- Exploring a Principled Framework for Deep Subspace Clustering (ICLR 2025 · similarity 0.88)
- You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering (NeurIPS 2025 · similarity 0.87)
- Interactive Deep Clustering via Value Mining (NeurIPS 2024 · similarity 0.86)
- Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation (AAAI 2024 · 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.