Less is More: A Closer Look at Semantic-based Few-Shot Learning

arXiv:2401.05010v2 Announce Type: replace
Abstract: Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional textual or linguistic information of these rare categories with a pre-trained language model to facilitate learning, thus partially alleviating the problem of insufficient supervision signals. However, the full potential of the textual information and pre-trained language model have been underestimated …

abstract arxiv challenge closer look cs.ai cs.cv deep learning few-shot few-shot learning images information learn look presenting researchers semantic textual type