Learning Data Augmentation Strategies for Object Detection

    公开(公告)号:US20190354817A1

    公开(公告)日:2019-11-21

    申请号:US16416848

    申请日:2019-05-20

    Applicant: Google LLC

    Abstract: Example aspects of the present disclosure are directed to systems and methods for learning data augmentation strategies for improved object detection model performance. In particular, example aspects of the present disclosure are directed to iterative reinforcement learning approaches in which, at each of a plurality of iterations, a controller model selects a series of one or more augmentation operations to be applied to training images to generate augmented images. For example, the controller model can select the augmentation operations from a defined search space of available operations which can, for example, include operations that augment the training image without modification of the locations of a target object and corresponding bounding shape within the image and/or operations that do modify the locations of the target object and bounding shape within the training image.

    Learning data augmentation strategies for object detection

    公开(公告)号:US11301733B2

    公开(公告)日:2022-04-12

    申请号:US16416848

    申请日:2019-05-20

    Applicant: Google LLC

    Abstract: Example aspects of the present disclosure are directed to systems and methods for learning data augmentation strategies for improved object detection model performance. In particular, example aspects of the present disclosure are directed to iterative reinforcement learning approaches in which, at each of a plurality of iterations, a controller model selects a series of one or more augmentation operations to be applied to training images to generate augmented images. For example, the controller model can select the augmentation operations from a defined search space of available operations which can, for example, include operations that augment the training image without modification of the locations of a target object and corresponding bounding shape within the image and/or operations that do modify the locations of the target object and bounding shape within the training image.

    Scale-Permuted Machine Learning Architecture

    公开(公告)号:US20220108204A1

    公开(公告)日:2022-04-07

    申请号:US17061355

    申请日:2020-10-01

    Applicant: Google LLC

    Abstract: A computer-implemented method of generating scale-permuted models can generate models having improved accuracy and reduced evaluation computational requirements. The method can include defining, by a computing system including one or more computing devices, a search space including a plurality of candidate permutations of a plurality of candidate feature blocks, each of the plurality of candidate feature blocks having a respective scale. The method can include performing, by the computing system, a plurality of search iterations by a search algorithm to select a scale-permuted model from the search space, the scale-permuted model based at least in part on a candidate permutation of the plurality of candidate permutations.

    Systems and Methods for Producing an Architecture of a Pyramid Layer

    公开(公告)号:US20220092387A1

    公开(公告)日:2022-03-24

    申请号:US17433677

    申请日:2020-02-25

    Applicant: Google LLC

    Abstract: A computing system for producing an architecture of a pyramid layer is disclosed. The computing system can include a controller model configured to generate new architectures for a pyramid layer that receives a plurality of input feature representations output by a backbone model and, in response, outputs a plurality of output feature representations. The plurality of input feature representations can have a plurality of different input resolutions, and the plurality of output feature representations can have a plurality of different output resolutions. The computing system can be configured to perform a plurality of iterations. For each iteration, the computing system can receive a new pyramid layer architecture as an output of the controller model and evaluate one or more performance characteristics of a machine-learned pyramidal feature model that includes the backbone model and one or more pyramid layers that have the new pyramid layer architecture.

    Learning Data Augmentation Strategies for Object Detection

    公开(公告)号:US20230274532A1

    公开(公告)日:2023-08-31

    申请号:US18313772

    申请日:2023-05-08

    Applicant: Google LLC

    Abstract: Example aspects of the present disclosure are directed to systems and methods for learning data augmentation strategies for improved object detection model performance. In particular, example aspects of the present disclosure are directed to iterative reinforcement learning approaches in which, at each of a plurality of iterations, a controller model selects a series of one or more augmentation operations to be applied to training images to generate augmented images. For example, the controller model can select the augmentation operations from a defined search space of available operations which can, for example, include operations that augment the training image without modification of the locations of a target object and corresponding bounding shape within the image and/or operations that do modify the locations of the target object and bounding shape within the training image.

Patent Agency Ranking