Few-shot learning (FSL) has emerged as an effective learning method and shows great
potential. Despite the recent creative works in tackling FSL tasks, learning valid information …

Deep learning approaches have recently raised the bar in many fields, from Natural
Language Processing to Computer Vision, by leveraging large amounts of data. However …

Deep learning-based models have been shown to outperform human beings in many
computer vision tasks with massive available labeled training data in learning. However …

We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL)
methods: the pre-trained knowledge is indeed a confounder that limits the performance. This …

Meta-learning has been the most common framework for few-shot learning in recent years. It
learns the model from collections of few-shot classification tasks, which is believed to have a …

Few-shot object detection has made encouraging progress by reconstructing novel class
objects using the feature representation learned upon a set of base classes. However, an …

Few-shot learning is a challenging problem since only a few examples are provided to
recognize a new class. Several recent studies exploit additional semantic information, eg …

Most of the few-shot learning methods learn to transfer knowledge from datasets with
abundant labeled data (ie, the base set). From the perspective of class space on base set …

The category gap between training and evaluation has been characterised as one of the
main obstacles to the success of Few-Shot Learning (FSL). In this paper, we for the first time …

Few-shot learning is a challenging task, which aims to learn a classifier for novel classes
with few examples. Pre-training based meta-learning methods effectively tackle the problem …