知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

19 records (took 0.048 seconds)

    ONLINE ADAPTATION OF SEGMENTATION MACHINE LEARNING SYSTEMS
    11.
    发明公开
    ONLINE ADAPTATION OF SEGMENTATION MACHINE LEARNING SYSTEMS 审中-公开

    公开(公告)号：US20240078797A1

    公开(公告)日：2024-03-07

    申请号：US18364728

    申请日：2023-08-03

    Applicant: QUALCOMM Incorporated

    Inventor： Kambiz AZARIAN YAZDI ,  Debasmit DAS ,  Hyojin PARK ,  Fatih Murat PORIKLI

    IPC: G06V10/778 ,  G06N3/0895 ,  G06V10/26 ,  G06V10/82

    CPC classification number: G06V10/778 ,  G06N3/0895 ,  G06V10/267 ,  G06V10/82

    Abstract: Techniques and systems are provided for performing online adaptation of machine learning model(s). For example, a process may include obtaining features extracted from a image by a machine learning model during inference and determining, by the machine learning model based on the features during inference, a plurality of keypoint estimates in the image and/or a bounding region estimate associated with an object in the image. The process may further include generating pseudo-label(s) based on the plurality of keypoint estimates and/or the bounding region estimate. The process may include determining at least one self-supervised loss based on the plurality of keypoint estimates and/or the bounding region estimate. The process may further include adapting, based on the at least one self-supervised loss, parameter(s) of the machine learning model. The process may include generating, using the machine learning model with the adapted parameter(s), a segmentation mask for the image (or another image).

    DOMAIN ADAPTATION FOR WIRELESS SENSING
    13.
    发明申请
    DOMAIN ADAPTATION FOR WIRELESS SENSING 有权

    公开(公告)号：US20230085880A1

    公开(公告)日：2023-03-23

    申请号：US17483434

    申请日：2021-09-23

    Applicant: QUALCOMM Incorporated

    Inventor： Jamie Menjay LIN ,  Debasmit DAS ,  Fatih Murat PORIKLI

    IPC: G06N3/04 ,  H04W64/00 ,  G06N3/08 ,  G06F17/16

    Abstract: Certain aspects of the present disclosure provide techniques for domain adaptation. An input tensor comprising channel state information (CSI) for a wireless signal is determined, where each channel in the input tensor corresponds to a respective degree of freedom (DoF) in the wireless signal. A domain-adapted tensor is generated by processing the input tensor using a domain-adaptation network comprising, for each respective DoF in the wireless signal, a respective convolution path. The domain-adapted tensor is provided to a neural network trained for position estimation.

    INSTANCE SEGMENTATION WITH DEPTH AND BOUNDARY LOSSES
    14.
    发明申请
    INSTANCE SEGMENTATION WITH DEPTH AND BOUNDARY LOSSES 有权

    公开(公告)号：US20240404003A1

    公开(公告)日：2024-12-05

    申请号：US18326437

    申请日：2023-05-31

    Applicant: QUALCOMM Incorporated

    Inventor： Debasmit DAS ,  Hyojin PARK ,  Shubhankar Mangesh BORSE ,  Yu FU ,  Oleksandr BAILO ,  Mohsen GHAFOORIAN ,  Fatih Murat PORIKLI

    IPC: G06T3/40

    Abstract: Certain aspects of the present disclosure provide techniques for training and using an instance segmentation neural network to detect instances of a target object in an image. An example method generally includes generating, through an instance segmentation neural network, a first mask output from a first mask generation branch of the network. The method further includes generating, through the instance segmentation neural network, a second mask output from a second, parallel, mask generation branch of the network. The second mask output is typically of a lower resolution than the first mask output. The method further includes combining the first mask output and second mask output to generate a combined mask output. Based on the combined mask output, an output of the instance segmentation neural network is generated. One or more actions are taken based on the generated output.

    MODEL DECORRELATION AND SUBSPACING FOR FEDERATED LEARNING
    16.
    发明公开
    MODEL DECORRELATION AND SUBSPACING FOR FEDERATED LEARNING 审中-公开

    公开(公告)号：US20240104367A1

    公开(公告)日：2024-03-28

    申请号：US17934098

    申请日：2022-09-21

    Applicant: QUALCOMM Incorporated

    Inventor： Jamie Menjay LIN ,  Debasmit DAS

    IPC: G06N3/08 ,  H04B17/391

    CPC classification number: G06N3/08 ,  H04B17/3913

    Abstract: Certain aspects of the present disclosure provide techniques and apparatus for training a machine learning model. An example method generally includes partitioning a machine learning model into a plurality of partitions. A request to update a respective partition of the plurality of partitions in the machine learning model is transmitted to each respective participating device of a plurality of participating devices in a federated learning scheme, and the request may specify that the respective partition is to be updated based on unique data at the respective participating device. Updates to one or more partitions in the machine learning model are received from the plurality of participating devices, and the machine learning model is updated based on the received updates.

    SEMANTIC-AWARE RANDOM STYLE AGGREGATION FOR SINGLE DOMAIN GENERALIZATION
    17.
    发明公开
    SEMANTIC-AWARE RANDOM STYLE AGGREGATION FOR SINGLE DOMAIN GENERALIZATION 审中-公开

    公开(公告)号：US20230376753A1

    公开(公告)日：2023-11-23

    申请号：US18157723

    申请日：2023-01-20

    Applicant: QUALCOMM Incorporated

    Inventor： Seokeon CHOI ,  Sungha CHOI ,  Seunghan YANG ,  Hyunsin PARK ,  Debasmit DAS ,  Sungrack YUN

    IPC: G06N3/08

    CPC classification number: G06N3/08

    Abstract: Systems and techniques are provided for training a neural network model or machine learning model. For example, a method of augmenting training data can include augmenting, based on a randomly initialized neural network, training data to generate augmented training data and aggregating data with a plurality of styles from the augmented training data to generate aggregated training data. The method can further include applying semantic-aware style fusion to the aggregated training data to generate fused training data and adding the fused training data as fictitious samples to the training data to generate updated training data for training the neural network model or machine learning model.

    MODEL DISENTANGLEMENT FOR DOMAIN ADAPTATION
    18.
    发明公开
    MODEL DISENTANGLEMENT FOR DOMAIN ADAPTATION 审中-公开

    公开(公告)号：US20230297653A1

    公开(公告)日：2023-09-21

    申请号：US17655506

    申请日：2022-03-18

    Applicant: QUALCOMM Incorporated

    Inventor： Debasmit DAS ,  Sungrack YUN ,  Fatih Murat PORIKLI

    IPC: G06F21/32 ,  G06N5/02

    CPC classification number: G06F21/32 ,  G06N5/022

    Abstract: Certain aspects of the present disclosure provide techniques for improved domain adaptation in machine learning. A feature tensor is generated by processing input data using a feature extractor. A first set of logits is generated by processing the feature tensor using a domain-agnostic classifier, and a second set of logits is generated by processing the feature tensor using a domain-specific classifier. A loss is computed based at least in part on the first set of logits and the second set of logits, where the loss includes a divergence loss component. The feature extractor, the domain-agnostic classifier, and the domain-specific classifier are refined using the loss.

Patent Agency Ranking