Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Model-Agnostic Boundary-Adversarial Sampling for Test-Time Generalization in Few-Shot learning
Jaekyeom Kim, Hyoungseok Kim, Gunhee Kim
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 MABAS test-time fine-tuning | STL · miniImageNet 5-way 1-shot | accuracy (%): 55.98 -> 60.19 | Improved |
| add MABAS test-time fine-tuning | FSwF · miniImageNet 5-way 5-shot | accuracy (%): 69.94 -> 78.28 | Improved |
| add MABAS test-time fine-tuning | MetaOptNet · miniImageNet 5-way 5-shot | accuracy (%): 78.55 -> 81.01 | Improved |
| add MABAS test-time fine-tuning | MetaOptNet-Proto · miniImageNet 5-way 5-shot | accuracy (%): 78.36 -> 82.70 | Improved |
| add MABAS test-time fine-tuning | STL · CIFAR-FS 5-way 5-shot | accuracy (%): 83.62 -> 84.29 | Improved |
| add MABAS test-time fine-tuning | FSwF · FC100 5-way 5-shot | accuracy (%): 49.75 -> 54.95 | Improved |
| add MABAS test-time fine-tuning | MetaOptNet-Proto · FC100 5-way 1-shot | accuracy (%): 40.60 -> 42.31 | Improved |
| add boundary-adversarial samples instead of naive fine-tuning on support only (ablation) | FSwF · miniImageNet 5-way 1-shot | accuracy (%): 55.73 -> 60.45 | Improved |
| add boundary-adversarial samples instead of naive fine-tuning on support only (ablation) | FSwF · miniImageNet 5-way 5-shot | accuracy (%): 70.14 -> 78.28 | Improved |
| naive fine-tuning on support samples only (ablation) | FSwF · miniImageNet 5-way 5-shot | accuracy (%): 69.94 -> 70.14 | No clear effect |
| add MABAS to ResNet-12 embedding | FSwF · miniImageNet 5-way 5-shot | accuracy (%): 69.94 -> 78.28 | Improved |
| add MABAS to Conv64 embedding | FSwF · miniImageNet 5-way 5-shot | accuracy (%): 71.89 -> 72.15 | No clear effect |
Closest papers by meaning
- MetaGAN: An Adversarial Approach to Few-Shot Learning (NeurIPS 2018 · similarity 0.88)
- Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning (ICLR 2021 · similarity 0.88)
- Provably Improving Generalization of Few-shot models with Synthetic Data (ICML 2025 · similarity 0.86)
- Mixture of Adversarial LoRAs: Boosting Robust Generalization in Meta-Tuning (NeurIPS 2024 · similarity 0.86)
- Generate Universal Adversarial Perturbations for Few-Shot Learning (NeurIPS 2024 · similarity 0.85)
- Few-Shot Adversarial Prompt Learning on Vision-Language Models (NeurIPS 2024 · 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.
