Few-Shot Learning Comparison Hub
3 papers - avg viability 7.3
Top Papers
- Local-Global Prompt Learning via Sparse Optimal Transport(8.0)
Improve few-shot classification and OOD detection by learning shared global prompts and class-specific local prompts with sparse optimal transport.
- SPRINT: Semi-supervised Prototypical Representation for Few-Shot Class-Incremental Tabular Learning(7.0)
SPRINT offers state-of-the-art few-shot class-incremental learning for tabular data, addressing challenges in domains like cybersecurity and healthcare.
- Noise-aware few-shot learning through bi-directional multi-view prompt alignment(7.0)
NA-MVP enhances few-shot learning by effectively distinguishing clean cues from noisy labels through innovative prompt alignment.