Research map / Label-efficient and robust learning / Semi-supervised learning
Dual Relation Semi-Supervised Multi-Label Learning
Lichen Wang, Yunyu Liu, Can Qin, Gan Sun, Yun Fu
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 domain adaptation (two-classifier adversarial alignment) (ablation) | DRML · CUB | MLL metrics | Improved |
| add label relation network (ablation) | DRML · CUB | MLL metrics | Improved |
| add pseudo label assignment (ablation) | DRML · CUB | MLL metrics | Improved |
| tune alpha near 0.5 (ablation) | DRML · multiple | performance | No clear effect |
| DRML vs best baseline in conventional MLL | DRML · Corel5K | F1: 0.3369 -> 0.3437 | Improved |
| DRML vs SAE on AWA | DRML · AWA | F1: 0.1742 vs 0.1523 | Hurt |
| DRML vs best baseline in zero-shot MLL | DRML · SUN zero-shot | F1: 0.2747 -> 0.2896 | Improved |
Closest papers by meaning
- Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning (ECCV 2024 · similarity 0.90)
- Correlation-Induced Label Prior for Semi-Supervised Multi-Label Learning (ICML 2024 · similarity 0.89)
- Collaborative Dual Representations for Semi-Supervised Partial Label Learning (AAAI 2026 · similarity 0.88)
- RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Rank Correlation between Labels (NeurIPS 2025 · similarity 0.88)
- LaSSL: Label-Guided Self-Training for Semi-supervised Learning (AAAI 2022 · similarity 0.88)
- Dual Set Multi-Label Learning (AAAI 2018 · similarity 0.88)
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.
