Research map / Label-efficient and robust learning / Recognition and long-tail
Task-Aware Variational Adversarial Active Learning
Check 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 |
|---|---|---|---|
| Add normalized task-loss ranking information to VAAL using RankCGAN | VAAL · CIFAR10 | accuracy | Helped |
| Add normalized task-loss ranking information to VAAL using RankCGAN | VAAL · CIFAR100 | accuracy | Helped |
| Add normalized task-loss ranking information to VAAL using RankCGAN | VAAL · Modified CIFAR10, imbalance ratio ×10 and ×100 | accuracy | Helped |
| Add normalized task-loss ranking information to VAAL using RankCGAN | VAAL · Caltech101 | accuracy | Helped |
| Add normalized task-loss ranking information to VAAL using RankCGAN | VAAL · Cityscapes | mean IoU | Helped |
| Replace the original learning-loss objective with ranking loss (ablation) | Learning loss · Modified CIFAR10, imbalance ratio ×10 | accuracy | Mixed |
| Use the original learning-loss architecture to add learning loss to VAAL instead of the proposed Ranker (ablation) | VAAL · Modified CIFAR10, imbalance ratio ×10 | accuracy | Mixed |
| Use the original learning-loss architecture to add learning loss to VAAL instead of the proposed Ranker (ablation) | VAAL · Modified CIFAR10, imbalance ratio ×10 | accuracy | Hurt |
| Use ranking loss instead of the original learning-loss objective (ablation) | Learning loss · Learning-loss module training | loss convergence | Helped |
| Use TA-VAAL instead of Core-set | Active learning selection · CIFAR10 | selection time per sample: 7.5 times | Hurt |
Closest papers by meaning
- AutoAL: Automated Active Learning with Differentiable Query Strategy Search (ICML 2025 · similarity 0.86)
- Variational Task Vector Composition (NeurIPS 2025 · similarity 0.85)
- Debiased Active Learning with Variational Gradient Rectifier (AAAI 2025 · similarity 0.83)
- Active Learning Guided by Efficient Surrogate Learners (AAAI 2024 · similarity 0.83)
- Adversarially Robust Multi-task Representation Learning (NeurIPS 2024 · similarity 0.82)
- One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models (ICLR 2024 · similarity 0.82)
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.