Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Interventional 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 |
|---|---|---|---|
| Apply IFSL to fine-tuning and meta-learning methods | Few-shot classifiers · miniImageNet and tieredImageNet | accuracy | Helped |
| Apply IFSL to few-shot learning | Fine-tuning and meta-learning methods · CUB cross-domain | accuracy: average 1.94% | Helped |
| Apply IFSL instead of using only the conventional classifier | Fine-tuning and meta-learning methods · Queries across all hardness levels | accuracy | Helped |
| Use a stronger backbone | Fine-tuning FSL · Hard queries | accuracy | Hurt |
| Use a stronger backbone | Fine-tuning FSL · Average across query hardness | accuracy | Helped |
| Use a stronger backbone | Meta-learning FSL · Hard queries | accuracy | Helped |
Closest papers by meaning
- Few-Shot Learning With Noisy Labels (CVPR 2022 · similarity 0.88)
- Pushing the Limit of Fine-Tuning for Few-Shot Learning: Where Feature Reusing Meets Cross-Scale Attention (AAAI 2024 · similarity 0.87)
- Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from a Conditional Causal Perspective (AAAI 2023 · similarity 0.87)
- Boosting Few-Shot Learning With Adaptive Margin Loss (CVPR 2020 · similarity 0.87)
- BECLR: Batch Enhanced Contrastive Few-Shot Learning (ICLR 2024 · similarity 0.86)
- Strong Baselines for Parameter-Efficient Few-Shot Fine-Tuning (AAAI 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.