By 2030, One-shot learning allows AI to recognize new objects in diverse settings from a single image, advancing beyond current models that need hundreds of examples.

One-shot learning: see only one labeled image of a new object, and then be able to recognize the object in real world scenes, to the extent that a typical human can (i.e. including in a wide variety of settings).

For example, see only one image of a platypus, and then be able to recognize platypuses in nature photos.

The system may train on labeled images of other objects.

Currently, deep networks often need hundreds of examples in classification tasks, but there has been work on one-shot learning for both classification and generative task.