公开(公告)号：US20220189612A1

公开(公告)日：2022-06-16

申请号：US17551050

申请日：2021-12-14

Applicant: Google LLC

Inventor： Xiaohua Zhai ,  Sylvain Gelly ,  Alexander Kolesnikov ,  Yin Ching Jessica Yung ,  Joan Puigcerver i Perez ,  Lucas Klaus Beyer ,  Neil Matthew Tinmouth Houlsby ,  Wen Yau Aaron Loh ,  Alan Prasana Karthikesalingam ,  Basil Mustafa ,  Jan Freyberg ,  Patricia Leigh MacWilliams ,  Vivek Natarajan

IPC: G16H30/40 ,  G16H50/20 ,  G06T7/00 ,  G06T3/40 ,  G06N3/02

Abstract: 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.

公开(公告)号：US20220375211A1

公开(公告)日：2022-11-24

申请号：US17737507

申请日：2022-05-05

Applicant: Google LLC

Inventor： Ilya Tolstikhin ,  Neil Matthew Tinmouth Houlsby ,  Alexander Kolesnikov ,  Lucas Klaus Beyer ,  Alexey Dosovitskiy ,  Mario Lucic ,  Xiaohua Zhai ,  Thomas Unterthiner ,  Daniel M. Keysers ,  Jakob D. Uszkoreit ,  Yin Ching Jessica Yung ,  Andreas Steiner

IPC: G06V10/82 ,  G06V10/764 ,  G06N3/04

Abstract: 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.

公开(公告)号：US12272442B2

公开(公告)日：2025-04-08

申请号：US17551050

申请日：2021-12-14

Applicant: Google LLC

Inventor： Xiaohua Zhai ,  Sylvain Gelly ,  Alexander Kolesnikov ,  Yin Ching Jessica Yung ,  Joan Puigcerver i Perez ,  Lucas Klaus Beyer ,  Neil Matthew Tinmouth Houlsby ,  Wen Yau Aaron Loh ,  Alan Prasana Karthikesalingam ,  Basil Mustafa ,  Jan Freyberg ,  Patricia Leigh MacWilliams ,  Vivek Natarajan

IPC: G16H30/40 ,  G06N3/02 ,  G06N3/096 ,  G06T3/4053 ,  G06T7/00 ,  G06V10/82 ,  G16H50/20

Abstract: 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.