公开(公告)号：US20210158093A1

公开(公告)日：2021-05-27

申请号：US16690695

申请日：2019-11-21

Applicant: Adobe Inc.

Inventor： Verena Kaynig-Fittkau ,  Sruthi Madapoosi Ravi ,  Richard Cohn ,  Nikolaos Barmpalios ,  Michael Kraley ,  Kanchana Sethu

IPC: G06K9/62 ,  G06K9/00 ,  G06N3/04

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating diverse and realistic synthetic documents using deep learning. In particular, the disclosed systems can utilize a trained neural network to generate realistic image layouts comprising page elements that comply with layout parameters. The disclosed systems can also generate synthetic content corresponding to the page elements within the image layouts. The disclosed systems insert the synthetic content into the corresponding page elements of documents based on the image layouts to generate synthetic documents.

公开(公告)号：US11544503B2

公开(公告)日：2023-01-03

申请号：US16885168

申请日：2020-05-27

Applicant: Adobe Inc.

Inventor： Christopher Tensmeyer ,  Vlad Ion Morariu ,  Varun Manjunatha ,  Tong Sun ,  Nikolaos Barmpalios ,  Kai Li ,  Handong Zhao ,  Curtis Wigington

IPC: G06K9/00 ,  G06K9/62 ,  G06N5/04 ,  G06V30/40

Abstract: A domain alignment technique for cross-domain object detection tasks is introduced. During a preliminary pretraining phase, an object detection model is pretrained to detect objects in images associated with a source domain using a source dataset of images associated with the source domain. After completing the pretraining phase, a domain adaptation phase is performed using the source dataset and a target dataset to adapt the pretrained object detection model to detect objects in images associated with the target domain. The domain adaptation phase may involve the use of various domain alignment modules that, for example, perform multi-scale pixel/path alignment based on input feature maps or perform instance-level alignment based on input region proposals.

公开(公告)号：US20220391768A1

公开(公告)日：2022-12-08

申请号：US17883811

申请日：2022-08-09

Applicant: Adobe Inc.

Inventor： Kai Li ,  Christopher Alan Tensmeyer ,  Curtis Michael Wigington ,  Handong Zhao ,  Nikolaos Barmpalios ,  Tong Sun ,  Varun Manjunatha ,  Vlad Ion Morariu

IPC: G06N20/00 ,  G06N3/04

Abstract: Adapting a machine learning model to process data that differs from training data used to configure the model for a specified objective is described. A domain adaptation system trains the model to process new domain data that differs from a training data domain by using the model to generate a feature representation for the new domain data, which describes different content types included in the new domain data. The domain adaptation system then generates a probability distribution for each discrete region of the new domain data, which describes a likelihood of the region including different content described by the feature representation. The probability distribution is compared to ground truth information for the new domain data to determine a loss function, which is used to refine model parameters. After determining that model outputs achieve a threshold similarity to the ground truth information, the model is output as a domain-agnostic model.

公开(公告)号：US12136287B2

公开(公告)日：2024-11-05

申请号：US17651433

申请日：2022-02-17

Applicant: Adobe Inc.

Inventor： Sanjeev Tagra ,  Shawn Alan Gaither ,  Shagun Kush ,  Samarth Gupta ,  Sachin Soni ,  Nikolaos Barmpalios ,  Abhishek Jain ,  Naqushab Neyazee

IPC: G06F17/00 ,  G06F40/106 ,  G06F40/114 ,  G06V30/414 ,  G06V30/416

Abstract: Techniques are disclosed for identifying asides within a document, and detecting a display order of contents based of the identified asides. In a document, an “aside” represents a content region of the document that is distinct from the main content regions, and may be visually distinguishable from the main content region. In an example, a document is received, where the document lacks identification of asides. The document is analyzed to identify asides within the document. A display order of contents within the document is then determined, based on the identified asides. For example, in the display order, the asides are ordered between two segments of the main content and/or at a beginning or an end of the main content, but may not be ordered to be embedded in between a segment of the main content. The document is displayed in accordance with the display order.

公开(公告)号：US11978272B2

公开(公告)日：2024-05-07

申请号：US17883811

申请日：2022-08-09

Applicant: Adobe Inc.

Inventor： Kai Li ,  Christopher Alan Tensmeyer ,  Curtis Michael Wigington ,  Handong Zhao ,  Nikolaos Barmpalios ,  Tong Sun ,  Varun Manjunatha ,  Vlad Ion Morariu

IPC: G06V30/413 ,  G06F17/18 ,  G06F18/213 ,  G06F18/2415 ,  G06N3/047 ,  G06N3/084 ,  G06N20/00 ,  G06N20/10 ,  G06V10/25 ,  G06V10/82 ,  G06V20/20 ,  G06V30/19 ,  G06V30/414

CPC classification number: G06V30/413 ,  G06F17/18 ,  G06F18/213 ,  G06F18/2415 ,  G06N3/047 ,  G06N3/084 ,  G06N20/00 ,  G06N20/10 ,  G06V10/25 ,  G06V10/82 ,  G06V20/20 ,  G06V30/19173 ,  G06V30/414

Abstract: Adapting a machine learning model to process data that differs from training data used to configure the model for a specified objective is described. A domain adaptation system trains the model to process new domain data that differs from a training data domain by using the model to generate a feature representation for the new domain data, which describes different content types included in the new domain data. The domain adaptation system then generates a probability distribution for each discrete region of the new domain data, which describes a likelihood of the region including different content described by the feature representation. The probability distribution is compared to ground truth information for the new domain data to determine a loss function, which is used to refine model parameters. After determining that model outputs achieve a threshold similarity to the ground truth information, the model is output as a domain-agnostic model.

公开(公告)号：US20230376687A1

公开(公告)日：2023-11-23

申请号：US17746779

申请日：2022-05-17

Applicant: ADOBE INC.

Inventor： Vlad Ion Morariu ,  Tong Sun ,  Nikolaos Barmpalios ,  Zilong Wang ,  Jiuxiang Gu ,  Ani Nenkova Nenkova ,  Christopher Tensmeyer

IPC: G06F40/279 ,  G06N5/02

CPC classification number: G06F40/279 ,  G06N5/022

Abstract: Embodiments are provided for facilitating multimodal extraction across multiple granularities. In one implementation, a set of features of a document for a plurality of granularities of the document is obtained. Via a machine learning model, the set of features of the document are modified to generate a set of modified features using a set of self-attention values to determine relationships within a first type of feature and a set of cross-attention values to determine relationships between the first type of feature and a second type of feature. Thereafter, the set of modified features are provided to a second machine learning model to perform a classification task.

公开(公告)号：US11689507B2

公开(公告)日：2023-06-27

申请号：US16695636

申请日：2019-11-26

Applicant: Adobe Inc.

Inventor： Nikolaos Barmpalios ,  Ruchi Rajiv Deshpande ,  Randy Lee Swineford ,  Nargol Rezvani ,  Andrew Marc Greene ,  Shawn Alan Gaither ,  Michael Kraley

IPC: H04L9/40 ,  G06Q30/0202 ,  G06N5/04 ,  G06N20/00

CPC classification number: H04L63/04 ,  G06N5/04 ,  G06N20/00 ,  G06Q30/0202

Abstract: Systems and techniques for privacy preserving document analysis are described that derive insights pertaining to a digital document without communication of the content of the digital document. To do so, the privacy preserving document analysis techniques described herein capture visual or contextual features of the digital document and creates a stamp representation that represents these features without included the content of the digital document. The stamp representation is projected into a stamp embedding space based on a stamp encoding model generated through machine learning techniques capturing feature patterns and interaction in the stamp representations. The stamp encoding model exploits these feature interactions to define similarity of source documents based on location within the stamp embedding space. Accordingly, the techniques described herein can determine a similarity of documents without having access to the documents themselves.

公开(公告)号：US11443193B2

公开(公告)日：2022-09-13

申请号：US16865605

申请日：2020-05-04

Applicant: Adobe Inc.

Inventor： Kai Li ,  Christopher Alan Tensmeyer ,  Curtis Michael Wigington ,  Handong Zhao ,  Nikolaos Barmpalios ,  Tong Sun ,  Varun Manjunatha ,  Vlad Ion Morariu

IPC: G06K9/00 ,  G06N3/08 ,  G06N20/10 ,  G06K9/62 ,  G06F17/18 ,  G06V10/75 ,  G06V20/20 ,  G06V30/413 ,  G06V30/414

Abstract: Adapting a machine learning model to process data that differs from training data used to configure the model for a specified objective is described. A domain adaptation system trains the model to process new domain data that differs from a training data domain by using the model to generate a feature representation for the new domain data, which describes different content types included in the new domain data. The domain adaptation system then generates a probability distribution for each discrete region of the new domain data, which describes a likelihood of the region including different content described by the feature representation. The probability distribution is compared to ground truth information for the new domain data to determine a loss function, which is used to refine model parameters. After determining that model outputs achieve a threshold similarity to the ground truth information, the model is output as a domain-agnostic model.

公开(公告)号：US11256913B2

公开(公告)日：2022-02-22

申请号：US16598680

申请日：2019-10-10

Applicant: Adobe Inc.

Inventor： Sanjeev Tagra ,  Shawn Alan Gaither ,  Shagun Kush ,  Samarth Gupta ,  Sachin Soni ,  Nikolaos Barmpalios ,  Abhishek Jain ,  Naqushab Neyazee

IPC: G06F17/00 ,  G06K9/00 ,  G06F40/106 ,  G06F40/114

Abstract: Techniques are disclosed for identifying asides within a document, and detecting a display order of contents based of the identified asides. In a document, an “aside” represents a content region of the document that is distinct from the main content regions, and may be visually distinguishable from the main content region. In an example, a document is received, where the document lacks identification of asides. The document is analyzed to identify asides within the document. A display order of contents within the document is then determined, based on the identified asides. For example, in the display order, the asides are ordered between two segments of the main content and/or at a beginning or an end of the main content, but may not be ordered to be embedded in between a segment of the main content. The document is displayed in accordance with the display order.

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.