Zero-shot learning

Zero-shot learning (ZSL) is a problem setup in machine learning where, at test time, a learner observes samples from classes which were not observed during training, and needs to predict their class. The name is a play on words based on the earlier concept of one-shot learning in computer vision, in which classification can be learned from only one example. Zero-shot methods generally work by associating observed and non-observed classes through auxiliary information that encodes observable distinguishing properties of objects. For example, given a set of images of animals to be classified, along with auxiliary textual descriptions of what animals look like, a model which has been trained to recognize horses, but has never been given a zebra, can still recognize a zebra when it also knows that zebras look like striped horses. This problem is widely studied in computer vision, natural language processing, and machine perception.

Zero-shot learning (ZSL) is a problem setup in machine learning where, at test time, a learner observes samples from classes which were not observed during training, and needs to predict their class. The name is a play on words based on the earlier concept of one-shot learning in computer vision, in which classification can be learned from only one example. Zero-shot methods generally work by associating observed and non-observed classes through auxiliary information that encodes observable distinguishing properties of objects. For example, given a set of images of animals to be classified, along with auxiliary textual descriptions of what animals look like, a model which has been trained to recognize horses, but has never been given a zebra, can still recognize a zebra when it also knows that zebras look like striped horses. This problem is widely studied in computer vision, natural language processing, and machine perception.

Text derived from https://en.wikipedia.org/w/index.php?oldid=1378219950 under CC BY-SA 4.0; modifications have been made.