Research

Efficient One-Shot Detection

Detecting objects from classes the model has never seen, given a single example — even when that example is a sketch.

One-shot detection involves the capability of a detection model to perform well in front of objects from unseen classes. In this case, the model just knows an example of the item to localize. We are developing efficient models that go beyond a simple image. For example, we combine our experience in the context of sketch-based representations to allow models to localize objects into a catalog of images using a sketch as a query.

The same idea powers our work on pattern spotting in historical documents, where a user marks one example and the model finds every other occurrence across a collection.

One-shot detection example 1
One-shot detection example 2
One-shot detection example 3
One-shot detection example 4
One-shot detection example 5
One-shot detection example 6
← All research