FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?

Understand

Few-shot learning aims to train models that can be generalized to novel classes with only a few samples.

• Recently, a line of works are proposed to enhance few-shot learning with accessible semantic information from class names.
• However, these works focus on improving existing modules such as visual prototypes and feature extractors of the standard few-shot learning framework.
• This limits the full potential use of semantic information.