Research map / Label-efficient and robust learning / Recognition and long-tail
Latent Discriminant Subspace Representations for Multi-View Outlier Detection
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 |
|---|---|---|---|
| use shared low-rank plus view-specific residual representation with new outlier score instead of pairwise-view methods | multi-view outlier detector · UCI datasets, 5% each of three outlier types | AUC: pima three views: 0.80 -> 0.83 (DMOD), 0.52 -> 0.83 (AP) | Helped |
| go from two to three views | proposed method and baselines · UCI datasets | AUC: zoo 0.89 -> 0.86; pima 0.85 -> 0.83 | Mixed |
| evaluate with only class and attribute outliers (10% each) | proposed method vs baselines · six datasets | AUC: pima 0.77 -> 0.80 vs DMOD; wdbc ties AP at 0.97 | Helped |
| increase outlier rate from 5% to 20% per type | proposed method · zoo | AUC | No clear effect |
| vary alpha and beta over {0.01 ... 10} (ablation) | proposed method · zoo | AUC | No clear effect |
| vary lambda in outlier score (ablation) | proposed method · zoo | AUC | No clear effect |
| double the number of views from two to four | proposed method · zoo | running time: 0.59 -> 0.73 | Hurt |
Closest papers by meaning
- Neighborhood Consensus Networks for Unsupervised Multi-view Outlier Detection (AAAI 2021 · similarity 0.92)
- Partial Multi-View Outlier Detection Based on Collective Learning (AAAI 2018 · similarity 0.90)
- RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples (ICML 2024 · similarity 0.85)
- ALTBI: Constructing Improved Outlier Detection Models via Optimization of Inlier-Memorization Effect (AAAI 2025 · similarity 0.84)
- Unveiling Multi-View Anomaly Detection: Intra-view Decoupling and Inter-view Fusion (AAAI 2025 · similarity 0.84)
- Quantile-Based Maximum Likelihood Training for Outlier Detection (AAAI 2024 · similarity 0.84)
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.