公开(公告)号：US20240028972A1

公开(公告)日：2024-01-25

申请号：US17815448

申请日：2022-07-27

Applicant: Adobe Inc.

Inventor： Christopher Tensmeyer ,  Nikolaos Barmpalios ,  Sruthi Madapoosi Ravi ,  Ruchi Deshpande ,  Varun Manjunatha ,  Smitha Bangalore Naresh ,  Priyank Mathur ,  Oghenetegiri Sido

IPC: G06N20/20 ,  G06K9/62

CPC classification number: G06N20/20 ,  G06K9/6262 ,  G06K9/6256

Abstract: Techniques for training for and determining a confidence of an output of a machine learning model are disclosed. Such techniques include, in some embodiments, receiving, from the machine learning model configured to receive information associated with a data object, information associated with a predicted structure for the data object; encoding, using a second machine learning model, the information associated with the predicted structure for the data object to produce encoded input channels; evaluating, using the second machine learning model, the information associated with the data object with the encoded input channels; and based on the evaluating, determining, using the second machine learning model, a probability of correctness of the predicted structure for the data object.

公开(公告)号：US20240135165A1

公开(公告)日：2024-04-25

申请号：US18047335

申请日：2022-10-18

Applicant: ADOBE INC.

Inventor： Varun Manjunatha ,  Sarthak Jain ,  Rajiv Bhawanji Jain ,  Ani Nenkova Nenkova ,  Christopher Alan Tensmeyer ,  Franck Dernoncourt ,  Quan Hung Tran ,  Ruchi Deshpande

IPC: G06N3/08 ,  G06F40/295

CPC classification number: G06N3/08 ,  G06F40/295

Abstract: One aspect of systems and methods for data correction includes identifying a false label from among predicted labels corresponding to different parts of an input sample, wherein the predicted labels are generated by a neural network trained based on a training set comprising training samples and training labels corresponding to parts of the training samples; computing an influence of each of the training labels on the false label by approximating a change in a conditional loss for the neural network corresponding to each of the training labels; identifying a part of a training sample of the training samples and a corresponding source label from among the training labels based on the computed influence; and modifying the training set based on the identified part of the training sample and the corresponding source label to obtain a corrected training set.

公开(公告)号：US20240232525A9

公开(公告)日：2024-07-11

申请号：US18048900

申请日：2022-10-24

Applicant: ADOBE INC.

Inventor： Rajiv Bhawanji Jain ,  Michelle Yuan ,  Vlad Ion Morariu ,  Ani Nenkova Nenkova ,  Smitha Bangalore Naresh ,  Nikolaos Barmpalios ,  Ruchi Deshpande ,  Ruiyi Zhang ,  Jiuxiang Gu ,  Varun Manjunatha ,  Nedim Lipka ,  Andrew Marc Greene

IPC: G06F40/20 ,  G06F40/169 ,  G06N3/08

CPC classification number: G06F40/20 ,  G06F40/169 ,  G06N3/08

Abstract: Systems and methods for document classification are described. Embodiments of the present disclosure generate classification data for a plurality of samples using a neural network trained to identify a plurality of known classes; select a set of samples for annotation from the plurality of samples using an open-set metric based on the classification data, wherein the annotation includes an unknown class; and train the neural network to identify the unknown class based on the annotation of the set of samples.

公开(公告)号：US20240135096A1

公开(公告)日：2024-04-25

申请号：US18048900

申请日：2022-10-23

Applicant: ADOBE INC.

Inventor： Rajiv Bhawanji Jain ,  Michelle Yuan ,  Vlad Ion Morariu ,  Ani Nenkova Nenkova ,  Smitha Bangalore Naresh ,  Nikolaos Barmpalios ,  Ruchi Deshpande ,  Ruiyi Zhang ,  Jiuxiang Gu ,  Varun Manjunatha ,  Nedim Lipka ,  Andrew Marc Greene

IPC: G06F40/20 ,  G06F40/169 ,  G06N3/08

CPC classification number: G06F40/20 ,  G06F40/169 ,  G06N3/08

Abstract: Systems and methods for document classification are described. Embodiments of the present disclosure generate classification data for a plurality of samples using a neural network trained to identify a plurality of known classes; select a set of samples for annotation from the plurality of samples using an open-set metric based on the classification data, wherein the annotation includes an unknown class; and train the neural network to identify the unknown class based on the annotation of the set of samples.