Google Inc.

Xiaohua Zhai

Neil Matthew Tinmouth Houlsby

Lucas Klaus Beyer

Alexander Kolesnikov

Sylvain Gelly

Alexey Dosovitskiy

Jakob D Uszkoreit

Thomas Unterthiner

Mostafa Dehghani

Dirk Weissenborn

Georg Heigold

Matthias Johannes Lorenz Minderer

Yin Ching Jessica Yung

Daniel M Keysers

Vivek Natarajan

Mario Lucic

Basil Mustafa

Joan Puigcerver I Perez

Ilya Tolstikhin

Alan Prasana Karthikesalingam

Patricia Leigh MacWilliams

Jan Freyberg

Andreas Peter Steiner

Wen Yau Aaron Loh

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using mixer neural networks. One of the methods includes obtaining one or more images comprising a plurality of pixels; determining, for each image of the one or more images, a plurality of image patches of the image, wherein each image patch comprises a different subset of the pixels of the image; processing, for each image of the one or more images, the corresponding plurality of image patches to generate an input sequence comprising a respective input element at each of a plurality of input positions, wherein a plurality of the input elements correspond to respective different image patches; and processing the input sequences using a neural network to generate a network output that characterizes the one or more images, wherein the neural network comprises one or more mixer neural network layers.

Multi-layer perceptron-based computer vision neural networks

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network to perform a downstream computer vision task. One of the methods includes pre-training an initial neural network that shares layers with the neural network to perform an initial computer vision task and then training the neural network on the downstream computer vision task.

Transfer learning between different computer vision tasks

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using self-attention based neural networks. One of the methods includes obtaining one or more images comprising a plurality of pixels; determining, for each image of the one or more images, a plurality of image patches of the image, wherein each image patch comprises a different subset of the pixels of the image; processing, for each image of the one or more images, the corresponding plurality of image patches to generate an input sequence comprising a respective input element at each of a plurality of input positions, wherein a plurality of the input elements correspond to respective different image patches; and processing the input sequences using a neural network to generate a network output that characterizes the one or more images, wherein the neural network comprises one or more self-attention neural network layers.

Processing images using self-attention based neural networks

Growing community of inventors

Zurich, Switzerland

Xiaohua Zhai