Research map / Label-efficient and robust learning / Recognition and long-tail
Label-Guided Representation Learning for Incomplete Multi-View Multi-Label Classification
Yang Li, Quanjiang Li, Tingjin Luo
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 category-specific conditional posteriors in fusion (ablation) | LGRL · Corel5k | AP: 0.446 -> 0.469 | Improved |
| add category-specific conditional posteriors in fusion (ablation) | LGRL · Pascal07 | AP: 0.548 -> 0.607 | Improved |
| add category-specific conditional posteriors in fusion (ablation) | LGRL · OBJECT | AP: 0.635 -> 0.705 | Improved |
| add category-specific conditional posteriors in fusion (ablation) | LGRL · Mirflickr | AP: 0.608 -> 0.653 | Improved |
| add task-relevant consistency constraints (ablation) | LGRL · Corel5k | AP: 0.455 -> 0.469 | Improved |
| add task-relevant consistency constraints (ablation) | LGRL · Pascal07 | AP: 0.582 -> 0.607 | Improved |
| add semantic alignment loss (ablation) | LGRL · Corel5k | AP: 0.464 -> 0.469 | Improved |
| add semantic alignment loss (ablation) | LGRL · Pascal07 | AP: 0.586 -> 0.607 | Improved |
| add semantic alignment loss (ablation) | LGRL · OBJECT | AP: 0.680 -> 0.705 | Improved |
| vary lambda and beta between 0.1 and 1 (ablation) | LGRL · Corel5k, OBJECT | AP | No clear effect |
Closest papers by meaning
- Incomplete Multi-View Multi-label Learning via Disentangled Representation and Label Semantic Embedding (CVPR 2025 · similarity 0.91)
- Partial Multi-View Multi-Label Classification via Semantic Invariance Learning and Prototype Modeling (ICML 2024 · similarity 0.91)
- Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label Classification (ICML 2025 · similarity 0.90)
- View-Category Interactive Sharing Transformer for Incomplete Multi-View Multi-Label Learning (CVPR 2024 · similarity 0.89)
- CFDM: Contrastive Fusion and Disambiguation for Multi-View Partial-Label Learning (AAAI 2025 · similarity 0.89)
- Theory-Inspired Deep Multi-View Multi-Label Learning with Incomplete Views and Noisy Labels (CVPR 2025 · similarity 0.89)
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.
