Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
A Nested Bi-level Optimization Framework for Robust Few Shot 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 NestedMAML task or instance weighting instead of MAML | MAML · CUB-200 and tieredImageNet, 3-shot and 5-shot, 90% FashionMNIST OOD | accuracy: 53.23% -> 59.18%; 61.84% -> 68.53%; 49.74% -> 57.17%; 56.45% -> 64.91% | Helped |
| Use NestedMAML task or instance weighting instead of MAML | MAML · 5-way 1-shot, SVHN and FashionMNIST OOD at 30% and 60% | accuracy: 41.07% -> 43.18%; 38.16% -> 41.30%; 39.73% -> 42.43%; 38.65% -> 40.81% | Helped |
| Use more adaptation steps during reweighting (ablation) | NestedMAML · Few-shot learning | performance | Helped |
Closest papers by meaning
- SHOT: Suppressing the Hessian along the Optimization Trajectory for Gradient-Based Meta-Learning (NeurIPS 2023 · similarity 0.89)
- Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning (ICML 2022 · similarity 0.89)
- How to Train Your MAML to Excel in Few-Shot Classification (ICLR 2022 · similarity 0.89)
- Meta-Learning with Implicit Gradients (NeurIPS 2019 · similarity 0.89)
- Probabilistic Model-Agnostic Meta-Learning (NeurIPS 2018 · similarity 0.89)
- Enabling Few-Shot Learning with PID Control: A Layer Adaptive Optimizer (ICML 2024 · similarity 0.88)
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.