Research map / Label-efficient and robust learning / Recognition and long-tail
Multi-Classifier Adversarial Optimization for Active Learning
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 |
|---|---|---|---|
| Use MAOAL with C3 discrepancy and its acquisition function instead of the compared alternatives (ablation) | Active learning on CIFAR-100 · CIFAR-100 | accuracy | Helped |
| Add a main classifier to the two auxiliary classifiers (ablation) | MAOAL on CIFAR-100 · CIFAR-100 | accuracy | Helped |
| Use the C3 metric, which includes inter-class correlation, instead of l1 prediction distance (ablation) | Adversarial active learning · Image classification | accuracy | Helped |
| Use the designed acquisition function S() instead of mean entropy sampling (ablation) | MAOAL · CIFAR-100 | accuracy | Helped |
| Apply MAOAL sample selection and training | Active learning on CIFAR-10 · CIFAR-10, 30%, 35%, and 40% labeled | accuracy: 0.7%, 0.6%, and 0.53% higher | Helped |
| Apply MAOAL sample selection and training | Active learning on CIFAR-100 · CIFAR-100, 15%, 25%, and 35% labeled | accuracy: 0.60%, 1.97%, and 1.27% higher | Helped |
| Apply MAOAL sample selection and training | Active learning on PASCAL VOC · PASCAL VOC | mean average precision | Helped |
Closest papers by meaning
- Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation (ICML 2025 · similarity 0.86)
- Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees (AAAI 2024 · similarity 0.86)
- Contextual Active Model Selection (NeurIPS 2024 · similarity 0.86)
- Identifying and Understanding Cross-Class Features in Adversarial Training (ICML 2025 · similarity 0.85)
- Fusing Conditional Submodular GAN and Programmatic Weak Supervision (AAAI 2024 · similarity 0.85)
- Enhancing the Adversarial Robustness via Manifold Projection (AAAI 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.