KNN Transformer with Pyramid Prompts for Few-Shot Learning

W Li, Q Wang, P Zhao, Y Yin - … of the 32nd ACM International Conference …, 2024 - dl.acm.org
Few-Shot Learning (FSL) aims to recognize new classes with limited labeled data. Recent
studies have attempted to address the challenge of rare samples with textual prompts to …

Enhancing Few-shot Classification through Token Selection for Balanced Learning

W Zeng, P Sun, H Zhang - 2024 International Joint Conference …, 2024 - ieeexplore.ieee.org
In recent years, patch-based approaches have shown promise in few-shot learning, with
further improvements observed through the use of self-supervised learning. However, we …