Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
Yaoyao Liu, Bernt Schiele, Qianru Sun
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 E3BM epoch-wise ensemble with hyperprior learners to SIB | SIB · miniImageNet 1-shot | accuracy (%): 70.0 -> 71.4 | Improved |
| add E3BM to SIB | SIB · tieredImageNet 1-shot | accuracy (%): 72.9 -> 75.6 | Improved |
| add E3BM to SIB | SIB · FC100 5-shot | accuracy (%): 55.9 -> 57.1 | Improved |
| add E3BM to MAML | MAML · miniImageNet 1-shot | accuracy (%): 48.70 -> 53.2 | Improved |
| add E3BM to MTL | MTL · miniImageNet 1-shot | accuracy (%): 63.4 -> 64.3 | Improved |
| add E3BM to MTL | MTL · FC100 5-shot | accuracy (%): 60.1 -> 60.5 | Improved |
| use transductive instead of inductive learning of hyperprior learners (ablation) | MTL+E3BM (LSTM) · miniImageNet 5-shot | accuracy (%): 81.0 -> 81.1 | Improved |
| use transductive instead of inductive learning (ablation) | MTL+E3BM (LSTM) · tieredImageNet 5-shot | accuracy (%): 85.0 -> 85.3 | Improved |
| use LSTM instead of FC hyperprior learner (ablation) | MTL+E3BM (transductive) · miniImageNet 5-shot | accuracy (%): 80.7 -> 81.1 | Improved |
| use LSTM instead of FC hyperprior learner (ablation) | SIB+E3BM · tieredImageNet 5-shot | accuracy (%): 83.8 -> 84.3 | Improved |
| use hyperprior-generated ensemble instead of 5 independent MAML learners (ablation) | MAML · miniImageNet 1-shot | accuracy (%): 52.1 -> 53.2 | Improved |
| use FC hyperprior vs 5x MAML (same ensemble size) (ablation) | MAML · miniImageNet 1-shot | accuracy (%): 52.1 -> 52.1 | No clear effect |
Closest papers by meaning
- Bayesian Low-Rank Learning (Bella): A Practical Approach to Bayesian Neural Networks (AAAI 2025 · similarity 0.85)
- SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning (ICML 2024 · similarity 0.85)
- Large Language Models to Enhance Bayesian Optimization (ICLR 2024 · similarity 0.84)
- Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment (NeurIPS 2025 · similarity 0.84)
- Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning (ICML 2024 · similarity 0.84)
- A Hierarchical Bayesian Model for Few-Shot Meta Learning (ICLR 2024 · similarity 0.84)
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.
