Research map / Label-efficient and robust learning / Recognition and long-tail
Enhanced Multi-Instance Partial Label Learning via Average Gradient Outer Product
Nan Cao, Xu Zhao, Teng Zhang
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 AGOP feature rescaling to the attention module (ablation) | AGOPMIPL · MNIST-MIPL (r=3) | accuracy: .891 -> 1.00 | Improved |
| add AGOP feature rescaling to the attention module (ablation) | AGOPMIPL · FMNIST-MIPL (r=3) | accuracy: .621 -> .752 | Improved |
| add AGOP feature rescaling to the attention module (ablation) | AGOPMIPL · CRC-MIPL-KMeansSeg (r=3) | accuracy: .618 -> .722 | Improved |
| add progressive label disambiguation (ablation) | AGOPMIPL · FMNIST-MIPL (r=3) | accuracy: .698 -> .752 | Improved |
| add progressive label disambiguation (ablation) | AGOPMIPL · MNIST-MIPL (r=3) | accuracy: .985 -> 1.00 | Improved |
| aggregate raw instance features instead of AGOP-transformed features for the bag representation (ablation) | AGOPMIPL · Appendix B | accuracy | Improved |
| vary number of prototypes np in {q/2, q, 2q} (ablation) | AGOPMIPL · SIVAL-MIPL | accuracy: less than 1.1 points | No clear effect |
| vary loss weights mu and gamma (ablation) | AGOPMIPL · FMNIST-MIPL (r=1), CRC-MIPL-SIFT | accuracy | No clear effect |
| use AGOPMIPL instead of FastMIPL under heavy candidate noise | AGOPMIPL · SIVAL-MIPL (r=5) | accuracy: .449 -> .544 | Improved |
| use AGOPMIPL instead of FastMIPL on Birdsong-MIPL at higher noise | AGOPMIPL · Birdsong-MIPL (r=3) | accuracy: .767 -> .742 | Hurt |
| increase candidate false-positive count r from 1 to 3 | baselines such as ProMIPL · MNIST-MIPL | accuracy: .999 -> .783 | Hurt |
Closest papers by meaning
- Multi-Instance Partial-Label Learning with Margin Adjustment (NeurIPS 2024 · similarity 0.91)
- Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning (NeurIPS 2023 · similarity 0.91)
- Fast Multi-Instance Partial-Label Learning (AAAI 2025 · similarity 0.91)
- Dual Graph Disambiguation for Multi-Instance Partial-Label Learning (AAAI 2026 · similarity 0.88)
- Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning (AAAI 2024 · similarity 0.87)
- Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning (NeurIPS 2025 · similarity 0.87)
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.
