Research map / Label-efficient and robust learning / Recognition and long-tail
General Partial Label Learning via Dual Bipartite Graph Autoencoder
Brian Chen, Bo Wu, Alireza Zareian, Hanwang Zhang, Shih-Fu Chang
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 |
|---|---|---|---|
| Use DB-GAE instead of the strongest baseline, PL-LEAF | GPLL face naming · MPII-MD | F1-score: 0.610 -> 0.768 | Improved |
| Use DB-GAE instead of the strongest baseline, SURE | GPLL face naming · MPII-MD | Accuracy: 48.7 % -> 76.5 % | Improved |
| Use DB-GAE instead of the strongest baseline, PL-AGGD | PLL face naming · M-VAD | Accuracy: 86.5 % -> 90.3 % | Improved |
| Add Graph Autoencoder (ablation) | DB-GAE · MPII-MD | F1-score: 0.614 -> 0.768 | Improved |
| Add Graph Autoencoder (ablation) | DB-GAE · MPII-MD | Accuracy: 62.9% -> 76.5% | Improved |
| Add Graph Autoencoder (ablation) | DB-GAE · M-VAD | Accuracy: 81.6% -> 90.3% | Improved |
| Add Dual Bipartite Graph architecture (ablation) | DB-GAE · MPII-MD | Accuracy: 68.4 % -> 76.5 % | Improved |
| Add Dual Bipartite Graph architecture (ablation) | DB-GAE · M-VAD | Accuracy: 88.3 % -> 90.3 % | Improved |
| Add Cross-Group Link (ablation) | DB-GAE · MPII-MD | F1-score: 0.730 -> 0.768 | Improved |
| Add Cross-Group Link (ablation) | DB-GAE · M-VAD | Accuracy: 89.2 % -> 90.3 % | Improved |
| Add Graph Attention (ablation) | DB-GAE · MPII-MD | F1-score: 0.743 -> 0.768 | Improved |
| Add Graph Attention (ablation) | DB-GAE · M-VAD | Accuracy: 87.3 % -> 90.3 % | Improved |
Closest papers by meaning
- GLDL: Graph Label Distribution Learning (AAAI 2024 · similarity 0.89)
- Dual Graph Disambiguation for Multi-Instance Partial-Label Learning (AAAI 2026 · similarity 0.88)
- Disentangled Partial Label Learning (AAAI 2024 · similarity 0.87)
- Realistic Evaluation of Deep Partial-Label Learning Algorithms (ICLR 2025 · similarity 0.87)
- Navigating Real-World Partial Label Learning: Unveiling Fine-Grained Images with Attributes (AAAI 2024 · similarity 0.87)
- Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency (ICML 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.
