Learning with limited labelled data, such as prompting, in-context learning, fine-tuning, meta-
learning or few-shot learning, aims to effectively train a model using only a small amount of …

Recent empirical evidence has driven conventional wisdom to believe that gradient-based
meta-learning (GBML) methods perform well at few-shot learning because they learn an …

Data augmentation has been an important ingredient for boosting performances of learned
models. Prior data augmentation methods for few-shot text classification have led to great …

Meta-learning algorithms are widely used for few-shot learning. For example, image
recognition systems that readily adapt to unseen classes after seeing only a few labeled …

The lack of sufficient annotated image data is a common issue in medical image
segmentation. For some organs and densities, the annotation may be scarce, leading to …

Learning with limited labelled data, such as few-shot learning, meta-learning or transfer
learning, aims to effectively train a model using only small amount of labelled samples …

We categorize meta-learning evaluation into two settings: $\textit {in-distribution} $[ID], in
which the train and test tasks are sampled $\textit {iid} $ from the same underlying task …

While learning with limited labelled data can improve performance when the labels are
lacking, it is also sensitive to the effects of uncontrolled randomness introduced by so-called …

Recent studies show that task distribution plays a vital role in the meta-learner's
performance. Conventional wisdom is that task diversity should improve the performance of …

The lack of sufficient annotated image data is a common issue in medical image
segmentation. For some organs and densities, the annotation may be scarce, leading to …