Research map / Label-efficient and robust learning / Recognition and long-tail
Adversarial Multi Class Learning under Weak Supervision with Performance Guarantees
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 |
|---|---|---|---|
| Adversarial multiclass learning with feasibility constraints from weak supervision statistics (AMCL-CC / AMCL-LR) vs. baselines | AMCL-CC · Animals with Attributes binary tasks (dolphin v. blue whale, seal v. walrus) | accuracy | Helped |
| AMCL-LR (logistic regression on ResNet-18 features) vs. ALL using same inputs and model | AMCL-LR · Animals with Attributes binary tasks | accuracy | Helped |
| Adversarial multiclass learning (AMCL-CC) vs. Dawid-Skene and majority vote | AMCL-CC · DomainNet clipart and quickdraw multiclass (5 classes) | accuracy | Helped |
| AMCL-CC on quickdraw where weak supervision sources are very inaccurate | AMCL-CC · DomainNet quickdraw | accuracy relative to best weak supervision source | Helped |
| AMCL-LR (logistic regression) as prediction model on DomainNet | AMCL-LR · DomainNet multiclass | accuracy | No clear effect |
Closest papers by meaning
- Adversarial Label Learning (AAAI 2019 · similarity 0.92)
- Generative Modeling Helps Weak Supervision (and Vice Versa) (ICLR 2023 · similarity 0.88)
- Fusing Conditional Submodular GAN and Programmatic Weak Supervision (AAAI 2024 · similarity 0.87)
- A General Framework for Learning from Weak Supervision (ICML 2024 · similarity 0.86)
- Weakly Supervised Contrastive Adversarial Training for Learning Robust Features from Semi-supervised Data (CVPR 2025 · similarity 0.85)
- Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data (ICLR 2025 · 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.