Comprehensive Guide to Zero-Shot and K-Shot Learning

Deep neural networks have achieved state-of-the-art for many computer vision tasks. However, much of this performance improvement can be accredited to their utilisation and reliance on large amounts of supervised information for learning. There are many practical cases in which such training data is not available. Few-shot learning as an approach is tasked with dealing with such issues. Few-shot learning is a type of supervised learning that is intended to rapidly generalise to new tasks containing only a few samples of supervised information based on prior knowledge.