2 papers
cs.CV2021
Episode Adaptive Embedding Networks for Few-shot Learning
Fangbing Liu, Qing Wang
Few-shot learning aims to learn a classifier using a few labelled instances for each class. Metric-learning approaches for few-shot learning embed instances into a high-dimensional…
cs.LG2019
Learning to Sample: an Active Learning Framework
Jingyu Shao, Qing Wang, Fangbing Liu
Meta-learning algorithms for active learning are emerging as a promising paradigm for learning the ``best'' active learning strategy. However, current learning-based active learnin…