Research map / Label-efficient and robust learning / Recognition and long-tail
Multi-View Partial Multi-Label Learning with Graph-Based Disambiguation
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 graph-based candidate label disambiguation stage (ablation) | GRADIS · Emotions, p=0.7 | average precision: 0.735 -> 0.772 | Helped |
| add graph-based candidate label disambiguation stage (ablation) | GRADIS · Youku25k, p=0.7 | average precision: 0.618 -> 0.664 | Helped |
| add graph-based candidate label disambiguation stage (ablation) | GRADIS · Youku50k, p=0.7 | average precision: 0.633 -> 0.688 | Helped |
| add graph-based candidate label disambiguation stage (ablation) | GRADIS · Emotions, p=0.7 | ranking loss: 0.236 -> 0.191 | Helped |
| add graph-based candidate label disambiguation stage (ablation) | GRADIS · Pascal, p=0.7 | average precision: 0.654 -> 0.640 | Hurt |
| add graph-based candidate label disambiguation stage (ablation) | GRADIS · Corel5k, p=0.7 | average precision: 0.464 -> 0.453 | Hurt |
| add graph-based candidate label disambiguation stage (ablation) | GRADIS · Yeast, p=0.3 | average precision: 0.765 -> 0.763 | No clear effect |
| add graph-based candidate label disambiguation stage (ablation) | GRADIS · all datasets, increasing noise p | average precision | Mixed |
| use GRADIS instead of concatenation-based LIFT on multi-view data | multi-label baselines · Mirflickr, p=0.7 | average precision: 0.474 -> 0.730 | Helped |
| raise thresholding parameter gamma above 0.1 | GRADIS · Yeast | average precision | Hurt |
Closest papers by meaning
- Multi-View Multi-Label Classification via View-Label Matching Selection (AAAI 2025 · similarity 0.90)
- CFDM: Contrastive Fusion and Disambiguation for Multi-View Partial-Label Learning (AAAI 2025 · similarity 0.88)
- A Two-Stage Information Extraction Network for Incomplete Multi-View Multi-Label Classification (AAAI 2024 · similarity 0.88)
- T-MDML: Triplet-based Multiple Distance Metric Learning for Multi-Instance Multi-Label Classification with Label Correlation (AAAI 2025 · similarity 0.86)
- Partial Multi-View Multi-Label Classification via Semantic Invariance Learning and Prototype Modeling (ICML 2024 · similarity 0.86)
- Incomplete Multi-View Multi-label Learning via Disentangled Representation and Label Semantic Embedding (CVPR 2025 · 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.