Research map / Architectures and efficiency / RNNs and normalization
Deep Subspace Clustering Networks
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 |
|---|---|---|---|
| Add a jointly trained self-expressive layer to the autoencoder | DSC-Net-L2 · Extended Yale B, 38 subjects | clustering error (%): 11.64 -> 2.67 | Helped |
| Use L2 rather than L1 regularization on the self-expressive coefficients (ablation) | DSC-Net · Extended Yale B, 38 subjects | clustering error (%): 3.33 -> 2.67 | Helped |
| Use L2 rather than L1 regularization on the self-expressive coefficients (ablation) | DSC-Net · Extended Yale B, 10 subjects | clustering error (%): 2.23 -> 1.59 | Helped |
| Use L2 rather than L1 regularization on the self-expressive coefficients (ablation) | DSC-Net · COIL20 | clustering error (%) | Mixed |
| Use pre-trained autoencoder features instead of jointly optimizing the clustering network | SSC and EDSC · Extended Yale B | clustering error (%) | Mixed |
| Use pre-trained convolutional autoencoder features | SSC and EDSC · ORL | clustering error (%) | Helped |
| Use a shallow, dimension-lifting architecture rather than a deep bottleneck architecture (ablation) | DSC-Net on COIL20 and COIL100 · COIL20 and COIL100 | clustering error (%) | Helped |
| Add a jointly trained self-expressive layer and learn affinities directly | DSC-Net-L2 · COIL20 | clustering error (%) | Helped |
| Add a jointly trained self-expressive layer and learn affinities directly | DSC-Net-L2 · ORL | clustering error (%) | Helped |
Closest papers by meaning
- Efficient Deep Embedded Subspace Clustering (CVPR 2022 · similarity 0.94)
- Exploring a Principled Framework for Deep Subspace Clustering (ICLR 2025 · similarity 0.94)
- A Critique of Self-Expressive Deep Subspace Clustering (ICLR 2021 · similarity 0.94)
- LRSC: Learning Representations for Subspace Clustering (AAAI 2021 · similarity 0.93)
- Neural Collaborative Subspace Clustering (ICML 2019 · similarity 0.92)
- Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning (NeurIPS 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.