US Patent 11126898 Computer vision classifier using item micromodels

Methods, storage media, and systems are disclosed. Exemplary implementations may: provide an encoding derived from an image of an item; provide a set of networks; individually apply the encoding to each network in the set of networks; generate, in response to the applying, a set of classification probabilities; identify a specific network in the set of networks which generated the largest classification probability in the set of classification probabilities; and associate the item with a specific class from the set of classes.