Zero-Shot Learning (ZSL)

What is Zero-Shot Learning?

Zero-Shot Learning (ZSL) involves a model providing a prediction for something it hasn’t seen during training. In other words, it can predict without requiring labelled data. For example, given a set of images of animals to be classified, along with some textual descriptions of what animals look like, a model which has been trained to recognize horses, but has never seen an image of a zebra, can still recognize a zebra when it also knows that zebras look like striped horses.