Patents by Inventor Abhishek Sinha

Abhishek Sinha has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20240375118
    Abstract: A pyramid lining insert/element for mill drum of a grinding mill, comprising of a structural and positional formation of pyramid inserts configured with a front lifter part that extends a first side of the liner member with a defined height and a real lifter part that extends to the rear side conforming shape of pyramid of the said liner member; wherein both the front and rear lifter part having an height; and wherein the said front and rear lifter part are adjacent to each other along the side of the said pyramid shaped lining member and have a front and rear support plate beneath the said front and rear lifter part in order to support the lifter plate and also to provide a robust and solid lining member.
    Type: Application
    Filed: November 26, 2022
    Publication date: November 14, 2024
    Inventors: Abhishek SINHA, Juan Eduardo Bustamante HERNANDEZ
  • Patent number: 11972466
    Abstract: A search system provides search results with images of products based on associations of primary products and secondary products from product image sets. The search system analyzes a product image set containing multiple images to determine a primary product and secondary products. Information associating the primary and secondary products are stored in a search index. When the search system receives a query image containing a search product, the search index is queried using the search product to identify search result images based on associations of products in the search index, and the result images are provided as a response to the query image.
    Type: Grant
    Filed: May 20, 2019
    Date of Patent: April 30, 2024
    Assignee: ADOBE INC
    Inventors: Jonas Dahl, Mausoom Sarkar, Hiresh Gupta, Balaji Krishnamurthy, Ayush Chopra, Abhishek Sinha
  • Patent number: 11829880
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating trained neural network with increased robustness against adversarial attacks by utilizing a dynamic dropout routine and/or a cyclic learning rate routine. For example, the disclosed systems can determine a dynamic dropout probability distribution associated with neurons of a neural network. The disclosed systems can further drop neurons from a neural network based on the dynamic dropout probability distribution to help neurons learn distinguishable features. In addition, the disclosed systems can utilize a cyclic learning rate routine to force copy weights of a copy neural network away from weights of an original neural network without decreasing prediction accuracy to ensure that the decision boundaries learned are different.
    Type: Grant
    Filed: October 24, 2022
    Date of Patent: November 28, 2023
    Assignee: Adobe Inc.
    Inventors: Mayank Singh, Nupur Kumari, Dhruv Khattar, Balaji Krishnamurthy, Abhishek Sinha
  • Patent number: 11734337
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for generating tags for an object portrayed in a digital image based on predicted attributes of the object. For example, the disclosed systems can utilize interleaved neural network layers of alternating inception layers and dilated convolution layers to generate a localization feature vector. Based on the localization feature vector, the disclosed systems can generate attribute localization feature embeddings, for example, using some pooling layer such as a global average pooling layer. The disclosed systems can then apply the attribute localization feature embeddings to corresponding attribute group classifiers to generate tags based on predicted attributes. In particular, attribute group classifiers can predict attributes as associated with a query image (e.g., based on a scoring comparison with other potential attributes of an attribute group).
    Type: Grant
    Filed: June 14, 2022
    Date of Patent: August 22, 2023
    Assignee: Adobe Inc.
    Inventors: Ayush Chopra, Mausoom Sarkar, Jonas Dahl, Hiresh Gupta, Balaji Krishnamurthy, Abhishek Sinha
  • Patent number: 11734565
    Abstract: Embodiments disclosed herein describe systems, methods, and products that generate trained neural networks that are robust against adversarial attacks. During a training phase, an illustrative computer may iteratively optimize a loss function that may include a penalty for ill-conditioned weight matrices in addition to a penalty for classification errors. Therefore, after the training phase, the trained neural network may include one or more well-conditioned weight matrices. The one or more well-conditioned weight matrices may minimize the effect of perturbations within an adversarial input thereby increasing the accuracy of classification of the adversarial input. By contrast, conventional training approaches may merely reduce the classification errors using backpropagation, and, as a result, any perturbation in an input is prone to generate a large effect on the output.
    Type: Grant
    Filed: June 3, 2022
    Date of Patent: August 22, 2023
    Assignee: Adobe Inc.
    Inventors: Mayank Singh, Abhishek Sinha, Balaji Krishnamurthy
  • Publication number: 20230107574
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating trained neural network with increased robustness against adversarial attacks by utilizing a dynamic dropout routine and/or a cyclic learning rate routine. For example, the disclosed systems can determine a dynamic dropout probability distribution associated with neurons of a neural network. The disclosed systems can further drop neurons from a neural network based on the dynamic dropout probability distribution to help neurons learn distinguishable features. In addition, the disclosed systems can utilize a cyclic learning rate routine to force copy weights of a copy neural network away from weights of an original neural network without decreasing prediction accuracy to ensure that the decision boundaries learned are different.
    Type: Application
    Filed: October 24, 2022
    Publication date: April 6, 2023
    Inventors: Mayank Singh, Nupur Kumari, Dhruv Khattar, Balaji Krishnamurthy, Abhishek Sinha
  • Patent number: 11481617
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating trained neural network with increased robustness against adversarial attacks by utilizing a dynamic dropout routine and/or a cyclic learning rate routine. For example, the disclosed systems can determine a dynamic dropout probability distribution associated with neurons of a neural network. The disclosed systems can further drop neurons from a neural network based on the dynamic dropout probability distribution to help neurons learn distinguishable features. In addition, the disclosed systems can utilize a cyclic learning rate routine to force copy weights of a copy neural network away from weights of an original neural network without decreasing prediction accuracy to ensure that the decision boundaries learned are different.
    Type: Grant
    Filed: January 22, 2019
    Date of Patent: October 25, 2022
    Assignee: Adobe Inc.
    Inventors: Mayank Singh, Nupur Kumari, Dhruv Khattar, Balaji Krishnamurthy, Abhishek Sinha
  • Patent number: 11468314
    Abstract: Embodiments disclosed herein describe systems, methods, and products that generate trained neural networks that are robust against adversarial attacks. During a training phase, an illustrative computer may iteratively optimize a loss function that may include a penalty for ill-conditioned weight matrices in addition to a penalty for classification errors. Therefore, after the training phase, the trained neural network may include one or more well-conditioned weight matrices. The one or more well-conditioned weight matrices may minimize the effect of perturbations within an adversarial input thereby increasing the accuracy of classification of the adversarial input. By contrast, conventional training approaches may merely reduce the classification errors using backpropagation, and, as a result, any perturbation in an input is prone to generate a large effect on the output.
    Type: Grant
    Filed: September 12, 2018
    Date of Patent: October 11, 2022
    Assignee: Adobe Inc.
    Inventors: Mayank Singh, Abhishek Sinha, Balaji Krishnamurthy
  • Publication number: 20220309093
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for generating tags for an object portrayed in a digital image based on predicted attributes of the object. For example, the disclosed systems can utilize interleaved neural network layers of alternating inception layers and dilated convolution layers to generate a localization feature vector. Based on the localization feature vector, the disclosed systems can generate attribute localization feature embeddings, for example, using some pooling layer such as a global average pooling layer. The disclosed systems can then apply the attribute localization feature embeddings to corresponding attribute group classifiers to generate tags based on predicted attributes. In particular, attribute group classifiers can predict attributes as associated with a query image (e.g., based on a scoring comparison with other potential attributes of an attribute group).
    Type: Application
    Filed: June 14, 2022
    Publication date: September 29, 2022
    Inventors: Ayush Chopra, Mausoom Sarkar, Jonas Dahl, Hiresh Gupta, Balaji Krishnamurthy, Abhishek Sinha
  • Publication number: 20220292356
    Abstract: Embodiments disclosed herein describe systems, methods, and products that generate trained neural networks that are robust against adversarial attacks. During a training phase, an illustrative computer may iteratively optimize a loss function that may include a penalty for ill-conditioned weight matrices in addition to a penalty for classification errors. Therefore, after the training phase, the trained neural network may include one or more well-conditioned weight matrices. The one or more well-conditioned weight matrices may minimize the effect of perturbations within an adversarial input thereby increasing the accuracy of classification of the adversarial input. By contrast, conventional training approaches may merely reduce the classification errors using backpropagation, and, as a result, any perturbation in an input is prone to generate a large effect on the output.
    Type: Application
    Filed: June 3, 2022
    Publication date: September 15, 2022
    Inventors: Mayank SINGH, Abhishek SINHA, Balaji KRISHNAMURTHY
  • Patent number: 11386144
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for generating tags for an object portrayed in a digital image based on predicted attributes of the object. For example, the disclosed systems can utilize interleaved neural network layers of alternating inception layers and dilated convolution layers to generate a localization feature vector. Based on the localization feature vector, the disclosed systems can generate attribute localization feature embeddings, for example, using some pooling layer such as a global average pooling layer. The disclosed systems can then apply the attribute localization feature embeddings to corresponding attribute group classifiers to generate tags based on predicted attributes. In particular, attribute group classifiers can predict attributes as associated with a query image (e.g., based on a scoring comparison with other potential attributes of an attribute group).
    Type: Grant
    Filed: September 9, 2019
    Date of Patent: July 12, 2022
    Assignee: Adobe Inc.
    Inventors: Ayush Chopra, Mausoom Sarkar, Jonas Dahl, Hiresh Gupta, Balaji Krishnamurthy, Abhishek Sinha
  • Patent number: 11308353
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for training a classification neural network to classify digital images in few-shot tasks based on self-supervision and manifold mixup. For example, the disclosed systems can train a feature extractor as part of a base neural network utilizing self-supervision and manifold mixup. Indeed, the disclosed systems can apply manifold mixup regularization over a feature manifold learned via self-supervised training such as rotation training or exemplar training. Based on training the feature extractor, the disclosed systems can also train a classifier to classify digital images into novel classes not present within the base classes used to train the feature extractor.
    Type: Grant
    Filed: October 23, 2019
    Date of Patent: April 19, 2022
    Assignee: Adobe Inc.
    Inventors: Mayank Singh, Puneet Mangla, Nupur Kumari, Balaji Krishnamurthy, Abhishek Sinha
  • Patent number: 11109380
    Abstract: Methods, systems, and devices for wireless communications are described. One method may include receiving, by a user equipment (UE) in a downlink shared data channel, a beam switch command instructing the UE to switch from a first uplink control beam to a second uplink control beam. The UE may select an uplink control beam to transmit acknowledgment feedback based on whether decoding the beam switch command is successful, and transmit, in an uplink control channel via the selected uplink control beam, the acknowledgment feedback indicating whether decoding the beam switch command was successful.
    Type: Grant
    Filed: March 4, 2019
    Date of Patent: August 31, 2021
    Assignee: QUALCOMM Incorporated
    Inventors: Makesh Pravin John Wilson, Sony Akkarakaran, Tao Luo, Yan Zhou, Xiao Feng Wang, Wooseok Nam, Abhishek Sinha
  • Publication number: 20210124993
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for training a classification neural network to classify digital images in few-shot tasks based on self-supervision and manifold mixup. For example, the disclosed systems can train a feature extractor as part of a base neural network utilizing self-supervision and manifold mixup. Indeed, the disclosed systems can apply manifold mixup regularization over a feature manifold learned via self-supervised training such as rotation training or exemplar training. Based on training the feature extractor, the disclosed systems can also train a classifier to classify digital images into novel classes not present within the base classes used to train the feature extractor.
    Type: Application
    Filed: October 23, 2019
    Publication date: April 29, 2021
    Inventors: Mayank Singh, Puneet Mangla, Nupur Kumari, Balaji Krishnamurthy, Abhishek Sinha
  • Patent number: 10959232
    Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive a signal identifying a first beam configuration and a second beam configuration to be used for performing a beamformed transmission of a physical uplink control channel (PUCCH) signal. The UE may determine, for a first PUCCH transmission occasion associated with the first beam configuration, that a communication metric associated with performing the beamformed transmission of the PUCCH signal using the first beam configuration fails to satisfy a threshold. The UE may perform, at a second PUCCH transmission occasion and based at least in part on the determining, the beamformed transmission of the PUCCH signal according to the second beam configuration.
    Type: Grant
    Filed: April 8, 2019
    Date of Patent: March 23, 2021
    Assignee: Qualcomm Incorporated
    Inventors: Xiao Feng Wang, Tao Luo, Sony Akkarakaran, Makesh Pravin John Wilson, Yan Zhou, Wooseok Nam, Abhishek Sinha, Juan Montojo
  • Publication number: 20210073267
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for generating tags for an object portrayed in a digital image based on predicted attributes of the object. For example, the disclosed systems can utilize interleaved neural network layers of alternating inception layers and dilated convolution layers to generate a localization feature vector. Based on the localization feature vector, the disclosed systems can generate attribute localization feature embeddings, for example, using some pooling layer such as a global average pooling layer. The disclosed systems can then apply the attribute localization feature embeddings to corresponding attribute group classifiers to generate tags based on predicted attributes. In particular, attribute group classifiers can predict attributes as associated with a query image (e.g., based on a scoring comparison with other potential attributes of an attribute group).
    Type: Application
    Filed: September 9, 2019
    Publication date: March 11, 2021
    Applicant: Adobe, Inc.
    Inventors: Ayush Chopra, Mausoom Sarkar, Jonas Dahl, Hiresh Gupta, Balaji Krishnamurthy, Abhishek Sinha
  • Publication number: 20210042625
    Abstract: Methods and systems are provided for facilitating the creation and utilization of a transformation function system capable of providing network agnostic performance improvement. The transformation function system receives a representation from a task neural network. The representation can be input into a composite function neural network of the transformation function system. A learned composite function can be generated using the composite function neural network. The composite function can be specifically constructed for the task neural network based on the input representation. The learned composite function can be applied to a feature embedding of the task neural network to transform the feature embedding. Transforming the feature embedding can optimize the output of the task neural network.
    Type: Application
    Filed: August 7, 2019
    Publication date: February 11, 2021
    Inventors: Ayush CHOPRA, Abhishek SINHA, Hiresh GUPTA, Mausoom SARKAR, Kumar AYUSH, Balaji KRISHNAMURTHY
  • Patent number: 10868698
    Abstract: A method and system are devised of moving at a NAS (1) a client (12, 13) with a MAC address, from a first VLAN to a second VLAN. A leaf is comprised of at least one intermediate L2 bridge/switch (5, 9) being connected to the NAS (1). The client (12, 13) is being connected to one (9) of the at least one intermediate L2 bridge/switches (5, 9) in the leaf. The method and system involve sending at the NAS (1) a first message downlink (31, 36) to intermediate L2 bridge/switches (5) in the leaf directly connected to the NAS.
    Type: Grant
    Filed: May 30, 2019
    Date of Patent: December 15, 2020
    Assignee: ALE USA INC.
    Inventors: Abhishek Sinha, Sandeep Kumar
  • Publication number: 20200382343
    Abstract: A method and system are devised of moving at a NAS (1) a client (12, 13) with a MAC address, from a first VLAN to a second VLAN. A leaf is comprised of at least one intermediate L2 bridge/switch (5, 9) being connected to the NAS (1). The client (12, 13) is being connected to one (9) of the at least one intermediate L2 bridge/switches (5, 9) in the leaf. The method and system involve sending at the NAS (1) a first message downlink (31, 36) to intermediate L2 bridge/switches (5) in the leaf directly connected to the NAS.
    Type: Application
    Filed: May 30, 2019
    Publication date: December 3, 2020
    Inventors: Abhishek SINHA, Sandeep KUMAR
  • Publication number: 20200372560
    Abstract: A search system provides search results with images of products based on associations of primary products and secondary products from product image sets. The search system analyzes a product image set containing multiple images to determine a primary product and secondary products. Information associating the primary and secondary products are stored in a search index. When the search system receives a query image containing a search product, the search index is queried using the search product to identify search result images based on associations of products in the search index, and the result images are provided as a response to the query image.
    Type: Application
    Filed: May 20, 2019
    Publication date: November 26, 2020
    Inventors: Jonas Dahl, Mausoom Sarkar, Hiresh Gupta, Balaji Krishnamurthy, Ayush Chopra, Abhishek Sinha