PROCESSING IMAGES USING MIXTURE OF EXPERTS

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating predictions about images. One of the systems includes a neural network comprising a sequence of one or more network blocks that are each configured to perform operations comprising: obtaini...

Full description

Saved in:
Bibliographic Details
Main Authors HOULSBY, Neil Matthew Tinmouth, MUSTAFA, Basil, PUIGCERVER I PEREZ, Joan, RIQUELME RUIZ, Carlos, NEUMANN, Maxim, KEYSERS, Daniel M, SUSANO PINTO, André, JENATTON, Rodolphe
Format Patent
LanguageEnglish
French
German
Published 06.12.2023
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating predictions about images. One of the systems includes a neural network comprising a sequence of one or more network blocks that are each configured to perform operations comprising: obtaining a block input that represents an intermediate representation of an input image; determining a plurality of patches of the block input or of an updated representation of the block input, wherein each patch comprises a different subset of elements of the block input or of the updated representation of the block input; assigning each patch to one or more respective expert modules of a plurality of expert modules of the network block; for each patch of the plurality of patches, processing the patch using the corresponding expert modules to generate respective module outputs; and generating a block output by combining the module outputs.
Bibliography:Application Number: EP20220736063