公开(公告)号：US20230325676A1

公开(公告)日：2023-10-12

申请号：US18333998

申请日：2023-06-13

Applicant: Google LLC

Inventor： Zizhao Zhang ,  Tomas Jon Pfister ,  Sercan Omer Arik ,  Mingfei Gao

IPC: G06N3/084 ,  G06N20/00 ,  G06F7/24 ,  G06N3/08 ,  G06F18/211 ,  G06F18/214

CPC classification number: G06N3/084 ,  G06N20/00 ,  G06F18/2155 ,  G06N3/08 ,  G06F18/211 ,  G06F7/24

Abstract: A method includes obtaining a set of unlabeled training samples. For each training sample in the set of unlabeled training samples generating, the method includes using a machine learning model and the training sample, a corresponding first prediction, generating, using the machine learning model and a modified unlabeled training sample, a second prediction, the modified unlabeled training sample based on the training sample, and determining a difference between the first prediction and the second prediction. The method includes selecting, based on the differences, a subset of the set of unlabeled training samples. For each training sample in the subset of the set of unlabeled training samples, the method includes obtaining a ground truth label for the training sample, and generating a corresponding labeled training sample based on the training sample paired with the ground truth label. The method includes training the machine learning model using the corresponding labeled training samples.

公开(公告)号：US20220375205A1

公开(公告)日：2022-11-24

申请号：US17664402

申请日：2022-05-20

Applicant: Google LLC

Inventor： Zizhao Zhang ,  Han Zhang ,  Long Zhao ,  Tomas Pfister

IPC: G06V10/77 ,  G06V10/764 ,  G06V10/22 ,  G06V10/44

Abstract: A method includes receiving image data including a series of image patches of an image. The method includes generating, using a first set of transformers of a vision transformer (V-T) model, a first set of higher order feature representations based on the series of image patches and aggregating the first set of higher order feature representations into a second set of higher order feature representations that is smaller than the first set. The method includes generating, using a second set of transformers of the V-T model, a third set of higher order feature representations based on the second set of higher order feature representations and aggregating the third set of higher order feature representations into a fourth set of higher order feature representations that is smaller than the third set. The method includes generating, using the V-T model, an image classification of the image based on the fourth set.

公开(公告)号：US11487970B2

公开(公告)日：2022-11-01

申请号：US17031144

申请日：2020-09-24

Applicant: Google LLC

Inventor： Sercan Omer Arik ,  Chen Xing ,  Zizhao Zhang ,  Tomas Jon Pfister

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: A method for jointly training a classification model and a confidence model. The method includes receiving a training data set including a plurality of training data subsets. From two or more training data subsets in the training data set, the method includes selecting a support set of training examples and a query set of training examples. The method includes determining, using the classification model, a centroid value for each respective class. For each training example in the query set of training examples, the method includes generating, using the classification model, a query encoding, determining a class distance measure, determining a ground-truth distance, and updating parameters of the classification model. For each training example in the query set of training examples identified as being misclassified, the method further includes generating a standard deviation value, sampling a new query, and updating parameters of the confidence model based on the new query encoding.