RECEPTIVE FIELD LEARNING FOR POOLED IMAGE FEATURES
    1.
    发明申请
    RECEPTIVE FIELD LEARNING FOR POOLED IMAGE FEATURES 有权
    用于漫游图像特征的接受现场学习

    公开(公告)号:US20130208977A1

    公开(公告)日:2013-08-15

    申请号:US13668188

    申请日:2012-11-02

    CPC classification number: G06K9/6256 G06K2009/4695

    Abstract: Systems and methods are disclosed for image classification by receiving an overcomplete set of spatial regions, jointly optimizing the classifier and the pooling region for each pooled feature; and performing incremental feature selection and retraining using a grafting process to efficiently train the classifier.

    Abstract translation: 公开了用于图像分类的系统和方法,其通过接收空间区域的不完整集合,联合优化每个合并特征的分类器和汇集区域; 并使用移植过程执行增量特征选择和再培训,以有效地训练分类器。

    Large-scale strongly supervised ensemble metric learning
    2.
    发明授权
    Large-scale strongly supervised ensemble metric learning 有权
    大规模强有力的监督综合度量学习

    公开(公告)号:US08873844B2

    公开(公告)日:2014-10-28

    申请号:US13682780

    申请日:2012-11-21

    CPC classification number: G06K9/6256 G06K9/6232

    Abstract: Systems and methods for metric learning include iteratively determining feature groups of images based on its derivative norm. Corresponding metrics of the feature groups are learned by gradient descent based on an expected loss. The corresponding metrics are combined to provide an intermediate metric matrix as a sparse representation of the images. A loss function of all metric parameters corresponding to features of the intermediate metric matrix are optimized, using a processor, to learn a final metric matrix. Eigenvalues of the final metric matrix are projected onto a simplex.

    Abstract translation: 度量学习的系统和方法包括基于其导数规范迭代确定图像的特征组。 通过基于预期损失的梯度下降来学习特征组的相应度量。 相应的度量被组合以提供作为图像的稀疏表示的中间度量矩阵。 使用处理器来优化对应于中间度量矩阵的特征的所有度量参数的损失函数来学习最终的度量矩阵。 最终公制矩阵的特征值被投影到单纯形上。

    Receptive field learning for pooled image features
    3.
    发明授权
    Receptive field learning for pooled image features 有权
    汇集图像特征的接受性现场学习

    公开(公告)号:US08781218B2

    公开(公告)日:2014-07-15

    申请号:US13668188

    申请日:2012-11-02

    CPC classification number: G06K9/6256 G06K2009/4695

    Abstract: Systems and methods are disclosed for image classification by receiving an overcomplete set of spatial regions, jointly optimizing the classifier and the pooling region for each pooled feature; and performing incremental feature selection and retraining using a grafting process to efficiently train the classifier.

    Abstract translation: 公开了用于图像分类的系统和方法,其通过接收空间区域的不完整集合,联合优化每个合并特征的分类器和汇集区域; 并使用移植过程执行增量特征选择和再培训,以有效地训练分类器。

    LARGE-SCALE STRONGLY SUPERVISED ENSEMBLE METRIC LEARNING
    4.
    发明申请
    LARGE-SCALE STRONGLY SUPERVISED ENSEMBLE METRIC LEARNING 有权
    大规模强有力的可控制度学习

    公开(公告)号:US20130129202A1

    公开(公告)日:2013-05-23

    申请号:US13682780

    申请日:2012-11-21

    CPC classification number: G06K9/6256 G06K9/6232

    Abstract: Systems and methods for metric learning include iteratively determining feature groups of images based on its derivative norm. Corresponding metrics of the feature groups are learned by gradient descent based on an expected loss. The corresponding metrics are combined to provide an intermediate metric matrix as a sparse representation of the images. A loss function of all metric parameters corresponding to features of the intermediate metric matrix are optimized, using a processor, to learn a final metric matrix. Eigenvalues of the final metric matrix are projected onto a simplex.

    Abstract translation: 度量学习的系统和方法包括基于其导数规范迭代确定图像的特征组。 通过基于预期损失的梯度下降来学习特征组的相应度量。 相应的度量被组合以提供作为图像的稀疏表示的中间度量矩阵。 使用处理器来优化对应于中间度量矩阵的特征的所有度量参数的损失函数来学习最终的度量矩阵。 最终公制矩阵的特征值被投影到单纯形上。

Patent Agency Ranking