-
公开(公告)号：US20210397876A1
公开(公告)日：2021-12-23
申请号：US16906954
申请日：2020-06-19
Applicant: ADOBE INC.
Inventor： Mayur Hemani , Siddhartha Gairola , Ayush Chopra , Balaji Krishnamurthy , Jonas Dahl
Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for one-shot and few-shot image segmentation on classes of objects that were not represented during training. In some embodiments, a dual prediction scheme may be applied in which query and support masks are jointly predicted using a shared decoder, which aids in similarity propagation between the query and support features. Additionally or alternatively, foreground and background attentive fusion may be applied to utilize cues from foreground and background feature similarities between the query and support images. Finally, to prevent overfitting on class-conditional similarities across training classes, input channel averaging may be applied for the query image during training. Accordingly, the techniques described herein may be used to achieve state-of-the-art performance for both one-shot and few-shot segmentation tasks.
-
公开(公告)号：US20210319473A1
公开(公告)日：2021-10-14
申请号：US17355907
申请日：2021-06-23
Applicant: Adobe Inc.
Inventor： Pankhri Singhai , Sundeep Parsa , Piyush Gupta , Nupur Kumari , Nikaash Puri , Mayank Singh , Eshita Shah , Balaji Krishnamurthy , Akash Rupela
Abstract: Machine-learning based multi-step engagement strategy modification is described. Rather than rely heavily on human involvement to manage content delivery over the course of a campaign, the described learning-based engagement system modifies a multi-step engagement strategy, originally created by an engagement-system user, by leveraging machine-learning models. In particular, these leveraged machine-learning models are trained using data describing user interactions with delivered content as those interactions occur over the course of the campaign. Initially, the learning-based engagement system obtains a multi-step engagement strategy created by an engagement-system user. As the multi-step engagement strategy is deployed, the learning-based engagement system randomly adjusts aspects of the sequence of deliveries for some users. Based on data describing the interactions of recipients with deliveries served according to both the user-created and random multi-step engagement strategies, the machine-learning models generate a modified multi-step engagement strategy.
-
公开(公告)号：US11080817B2
公开(公告)日：2021-08-03
申请号：US16673574
申请日：2019-11-04
Applicant: Adobe Inc.
Inventor： Kumar Ayush , Surgan Jandial , Mayur Hemani , Balaji Krishnamurthy , Ayush Chopra
Abstract: Generating a synthesized image of a person wearing clothing is described. A two-dimensional reference image depicting a person wearing an article of clothing and a two-dimensional image of target clothing in which the person is to be depicted as wearing are received. To generate the synthesized image, a warped image of the target clothing is generated via a geometric matching module, which implements a machine learning model trained to recognize similarities between warped and non-warped clothing images using multi-scale patch adversarial loss. The multi-scale patch adversarial loss is determined by sampling patches of different sizes from corresponding locations of warped and non-warped clothing images. The synthesized image is generated on a per-person basis, such that the target clothing fits the particular body shape, pose, and unique characteristics of the person.
-
公开(公告)号：US20210133919A1
公开(公告)日：2021-05-06
申请号：US16673574
申请日：2019-11-04
Applicant: Adobe Inc.
Inventor： Kumar Ayush , Surgan Jandial , Mayur Hemani , Balaji Krishnamurthy , Ayush Chopra
Abstract: Generating a synthesized image of a person wearing clothing is described. A two-dimensional reference image depicting a person wearing an article of clothing and a two-dimensional image of target clothing in which the person is to be depicted as wearing are received. To generate the synthesized image, a warped image of the target clothing is generated via a geometric matching module, which implements a machine learning model trained to recognize similarities between warped and non-warped clothing images using multi-scale patch adversarial loss. The multi-scale patch adversarial loss is determined by sampling patches of different sizes from corresponding locations of warped and non-warped clothing images. The synthesized image is generated on a per-person basis, such that the target clothing fits the particular body shape, pose, and unique characteristics of the person.
-
公开(公告)号：US10755199B2
公开(公告)日：2020-08-25
申请号：US15608517
申请日：2017-05-30
Applicant: Adobe Inc.
Inventor： Mausoom Sarkar , Balaji Krishnamurthy , Abhishek Sinha , Aahitagni Mukherjee
Abstract: An introspection network is a machine-learned neural network that accelerates training of other neural networks. The introspection network receives a weight history for each of a plurality of weights from a current training step for a target neural network. A weight history includes at least four values for the weight that are obtained during training of the target neural network up to the current step. The introspection network then provides, for each of the plurality of weights, a respective predicted value, based on the weight history. The predicted value for a weight represents a value for the weight in a future training step for the target neural network. Thus, the predicted value represents a jump in the training steps of the target neural network, which reduces the training time of the target neural network. The introspection network then sets each of the plurality of weights to its respective predicted value.
-
Patent Agency Ranking
公开(公告)号：US10699321B2
公开(公告)日：2020-06-30
申请号：US15785934
申请日：2017-10-17
Applicant: Adobe Inc.
Inventor： Balaji Krishnamurthy , Nikaash Puri
Abstract: A digital medium environment is described to facilitate recommendations based on vectors generated using feature word embeddings. A recommendation system receives data that describes at least one attribute for a user profile, at least one item, and an interaction between the user profile and the at least one item. The recommendation system associates each user profile attribute, each item, and each interaction between a user profile and an item as a word, using natural language processing, and combines the words into sentences. The sentences are input to a word embedding model to determine feature vector representations describing relationships between the user profile attributes, items, and explicit and implicit interactions. From the feature vector representations, the recommendation system ascertains a similarity between different features. Thus, the recommendation system can provide customized recommendations based on implicit interactions, even for a user profile that is not associated with any historical interaction data.
-
公开(公告)号：US20200053403A1
公开(公告)日：2020-02-13
申请号：US16057729
申请日：2018-08-07
Applicant: Adobe Inc.
Inventor： Pankhri Singhai , Sundeep Parsa , Piyush Gupta , Nikaash Puri , Eshita Shah , Balaji Krishnamurthy , Nupur Kumari , Mayank Singh , Akash Rupela
IPC: H04N21/25 , G06N99/00 , H04N21/475 , H04N21/258 , H04N21/2668
Abstract: Machine-learning based multi-step engagement strategy generation and visualization is described. Rather than rely heavily on human involvement to create delivery strategies, the described learning-based engagement system generates multi-step engagement strategies by leveraging machine-learning models trained using data describing historical user interactions with content delivered in connection with historical campaigns. Initially, the learning-based engagement system obtains data describing an entry condition and an exit condition for a campaign. Based on the entry and exit condition, the learning-based engagement system utilizes the machine-learning models to generate a multi-step engagement strategy, which describes a sequence of content deliveries that are to be served to a particular client device user (or segment of client device users). Once the multi-step engagement strategies are generated, the learning-based engagement system may also generate visualizations of the strategies that can be output for display.
-
公开(公告)号：US20200051118A1
公开(公告)日：2020-02-13
申请号：US16057743
申请日：2018-08-07
Applicant: Adobe Inc.
Inventor： Pankhri Singhai , Sundeep Parsa , Piyush Gupta , Nupur Kumari , Nikaash Puri , Mayank Singh , Eshita Shah , Balaji Krishnamurthy , Akash Rupela
Abstract: Machine-learning based multi-step engagement strategy modification is described. Rather than rely heavily on human involvement to manage content delivery over the course of a campaign, the described learning-based engagement system modifies a multi-step engagement strategy, originally created by an engagement-system user, by leveraging machine-learning models. In particular, these leveraged machine-learning models are trained using data describing user interactions with delivered content as those interactions occur over the course of the campaign. Initially, the learning-based engagement system obtains a multi-step engagement strategy created by an engagement-system user. As the multi-step engagement strategy is deployed, the learning-based engagement system randomly adjusts aspects of the sequence of deliveries for some users. Based on data describing the interactions of recipients with deliveries served according to both the user-created and random multi-step engagement strategies, the machine-learning models generate a modified multi-step engagement strategy.
-
59.发明授权公开(公告)号：US10423828B2
公开(公告)日：2019-09-24
申请号：US15843953
申请日：2017-12-15
Applicant: Adobe Inc.
Inventor： Shagun Sodhani , Kartikay Garg , Balaji Krishnamurthy
Abstract: Techniques for determining reading order in a document. A current labeled text run (R1), RIGHT text run (R1) and DOWN text run (R3) are generated. The R1 labeled text run is processed by a first LSTM, the R2 labeled text run is processed by a second LSTM, and the R3 labeled text run is processed by a third LSTM, wherein each of the LSTMs generates a respective internal representation (R1′, R2′ and R3′). Deep learning tools other than LSTMs can be used, as will be appreciated. The respective internal representations R1′, R2′ and R3′ are concatenated or otherwise combined into a vector or tensor representation and provided to a classifier network that generates a predicted label for a next text run as RIGHT, DOWN or EOS in the reading order of the document.
-
公开(公告)号：US20190156216A1
公开(公告)日：2019-05-23
申请号：US15815899
申请日：2017-11-17
Applicant: Adobe Inc.
Inventor： Piyush Gupta , Nikaash Puri , Balaji Krishnamurthy
Abstract: A technique is disclosed for generating class level rules that globally explain the behavior of a machine learning model, such as a model that has been used to solve a classification problem. Each class level rule represents a logical conditional statement that, when the statement holds true for one or more instances of a particular class, predicts that the respective instances are members of the particular class. Collectively, these rules represent the pattern followed by the machine learning model. The techniques are model agnostic, and explain model behavior in a relatively easy to understand manner by outputting a set of logical rules that can be readily parsed. Although the techniques can be applied to any number of applications, in some embodiments, the techniques are suitable for interpreting models that perform the task of classification. Other machine learning model applications can equally benefit.
-
-
-
-
-
-
-
-
-
Search Results
123
records
(took 0.03 seconds)
