The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …

Learning from a limited number of samples is challenging since the learned model can
easily become overfitted based on the biased distribution formed by only a few training …

Existing few-shot learning (FSL) methods rely on training with a large labeled dataset, which
prevents them from leveraging abundant unlabeled data. From an information-theoretic …

Few-shot or one-shot learning of classifiers requires a significant inductive bias towards the
type of task to be learned. One way to acquire this is by meta-learning on tasks similar to the …

Meta-learning algorithms aim to learn two components: a model that predicts targets for a
task, and a base learner that updates that model when given examples from a new task. This …

Conventional image classifiers are trained by randomly sampling mini-batches of images.
To achieve state-of-the-art performance, practitioners use sophisticated data augmentation …

Supervised machine learning has several drawbacks that make it difficult to use in many
situations. Drawbacks include heavy reliance on massive training data, limited …

Pre-trained vision-language models have inspired much research on few-shot learning.
However, with only a few training images, there exist two crucial problems:(1) the visual …

Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the
context of reinforcement learning, meta-learning algorithms acquire reinforcement learning …

Few-shot learning methods offer pre-training techniques optimized for easier later
adaptation of the model to new classes (unseen during training) using one or a few …