Research map / Label-efficient and robust learning / Recognition and long-tail
Robust Multi-View Subspace Learning through Dual Low-Rank Decompositions
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 |
|---|---|---|---|
| dual low-rank decomposition with supervised graph regularizers (RMSL) vs SRRS | subspace learning · CMU-PIE clean Case 1 | accuracy (%): 78.27±0.04 -> 89.15±0.06 | Helped |
| RMSL vs LRCS (needs view labels at training) | subspace learning · CMU-PIE corrupted Case 1 | accuracy (%): 78.98±0.03 -> 82.12±0.08 | Helped |
| RMSL vs LRCS | subspace learning · CMU-PIE clean Case 5 | accuracy (%): 74.84±0.04 -> 75.16±0.12 | No clear effect |
| RMSL vs LRCS | subspace learning · CMU-PIE clean Case 7 | accuracy (%): 36.17±0.01 -> 37.14±0.08 | No clear effect |
| use supervised class label (LDA) in place of unsupervised PCA | subspace learning · CMU-PIE corrupted Case 1 | accuracy (%): 64.87±0.32 -> 26.71±0.20 | Hurt |
| increase alpha of graph regularizer from near 0 to about 10^2 (ablation) | RMSL · CMU-PIE 2-view C02&C27 | accuracy | Helped |
| RMSL optimization vs LRCS training time | training · CMU-PIE 5 views | training time (s): 2311.1 -> 510.4 | Helped |
| increase number of views from 2 to 5 | all methods · CMU-PIE clean | accuracy (%): 89.15±0.06 -> 37.14±0.08 (RMSL Case 1 vs Case 7) | Hurt |
Closest papers by meaning
- Unified View Extraction with Low-Rankness and Smoothness Fusion for Multi-View Subspace Clustering (AAAI 2026 · similarity 0.89)
- Learning Subspace-Preserving Sparse Attention Graphs from Heterogeneous Multiview Data (NeurIPS 2026 · similarity 0.85)
- From Dictionary to Tensor: A Scalable Multi-View Subspace Clustering Framework with Triple Information Enhancement (NeurIPS 2024 · similarity 0.84)
- Contrastive Multi-view Subspace Clustering via Tensor Transformers Autoencoder (AAAI 2025 · similarity 0.84)
- Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs (ICLR 2025 · similarity 0.84)
- Rethinking Multi-view Representation Learning via Distilled Disentangling (CVPR 2024 · similarity 0.83)
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.