Research map / Label-efficient and robust learning / Recognition and long-tail
A Deep Matrix Factorization Method for Learning Attribute Representations
George Trigeorgis, Konstantinos Bousmalis, Stefanos P. Zafeiriou, Björn Wolfgang Schuller
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 |
|---|---|---|---|
| add depth (second factorization layer) to Semi-NMF | Semi-NMF · CMU Multi-PIE identity classification | accuracy: 36.46 -> 61.22 | Improved |
| add depth to Semi-NMF | Semi-NMF · CMU Multi-PIE expression classification | accuracy: 81.50 -> 80.54 | No clear effect |
| add attribute supervision and depth (Deep WSF) to Deep Semi-NMF | Deep Semi-NMF · CMU Multi-PIE identity classification | accuracy: 61.22 -> 65.17 | Improved |
| add depth to WSF (Deep WSF vs WSF) | WSF · CMU Multi-PIE identity classification | accuracy: 63.81 -> 65.17 | Improved |
| use all attributes (WSF-MA) instead of one attribute (WSF) | WSF · CMU Multi-PIE identity classification | accuracy: 63.81 -> 64.08 | Improved |
| add depth to Semi-NMF | Semi-NMF · CMU PIE reconstruction (70 components) | reconstruction error: 4.13 vs. 4.39 | No clear effect |
| add supervised pre-training on XM2VTS before unsupervised fine-tuning (ablation) | Deep Semi-NMF · CMU PIE clustering | accuracy | Improved |
| use IGO features instead of pixel intensities | Deep Semi-NMF · XM2VTS / CMU PIE clustering | accuracy | Improved |
Closest papers by meaning
- Multi-View Clustering via Deep Matrix Factorization (AAAI 2017 · similarity 0.88)
- Dual-Constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior (IJCV 2021 · similarity 0.86)
- Non-Negative Tensor Factorization Based Bi-Clustering on Anchor Graphs (TPAMI 2026 · similarity 0.86)
- Exploring a Principled Framework for Deep Subspace Clustering (ICLR 2025 · similarity 0.86)
- Exponentially Convergent Algorithms for Supervised Matrix Factorization (NeurIPS 2023 · similarity 0.86)
- Statistically Optimal $K$-means Clustering via Nonnegative Low-rank Semidefinite Programming (ICLR 2024 · 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.
