利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

41 条记录 (耗时 0.024 秒)

    Methods, devices and media providing an integrated teacher-student system
    1.
    发明授权
    Methods, devices and media providing an integrated teacher-student system 有权

    公开(公告)号：US11900260B2

    公开(公告)日：2024-02-13

    申请号：US16810524

    申请日：2020-03-05

    申请人： Deepak Sridhar ,  Juwei Lu

    发明人： Deepak Sridhar ,  Juwei Lu

    IPC分类号： G06N3/08 ,  G06N3/088 ,  G06N3/045

    CPC分类号： G06N3/088 ,  G06N3/045 ,  G06N3/08

    摘要： Methods, devices and processor-readable media for an integrated teacher-student machine learning system. One or more teacher-student modules are trained as part of the teacher neural network training. Each student sub-network uses a portion of the teacher neural network to generate an intermediate feature map, then provides the intermediate feature map to a student sub-network to generate inferences. The student sub-network may use a feature enhancement block to map the intermediate feature map to a subsequent feature map. A compression block may be used to compress intermediate feature map data for transmission in some embodiments.

    Semi-supervised hybrid clustering/classification system
    6.
    发明授权
    Semi-supervised hybrid clustering/classification system 有权

    公开(公告)号：US11023710B2

    公开(公告)日：2021-06-01

    申请号：US16280760

    申请日：2019-02-20

    申请人： Peng Dai ,  Juwei Lu ,  Bharath Sekar ,  Wei Li ,  Jianpeng Xu ,  Ruiwen Li

    发明人： Peng Dai ,  Juwei Lu ,  Bharath Sekar ,  Wei Li ,  Jianpeng Xu ,  Ruiwen Li

    IPC分类号： G06K9/00 ,  G06K9/62 ,  G06N20/00 ,  G06F16/75

    摘要： System and method for classifying data objects occurring in an unstructured dataset, comprising: extracting feature vectors from the unstructured dataset, each feature vector representing an occurrence of a data object in the unstructured dataset; classifying the feature vectors into feature vector sets that each correspond to a respective object class from a plurality of object classes; for each feature vector set: performing multiple iterations of a clustering operation, each iteration including clustering feature vectors from the feature vector set into clusters of similar feature vectors and identifying outlier feature vectors, wherein for at least one iteration after a first iteration of the clustering operation, outlier feature vectors identified in a previous iteration are excluded from the clustering operation; and outputting a key cluster for the feature vector set from a final iteration of the multiple iterations, the key cluster including a greater number of similar feature vectors than any of the other clusters of the final iteration; and assembling a dataset that includes at least the feature vectors from the key clusters of the feature vector sets.

    SEMI-SUPERVISED HYBRID CLUSTERING/CLASSIFICATION SYSTEM
    7.
    发明申请
    SEMI-SUPERVISED HYBRID CLUSTERING/CLASSIFICATION SYSTEM 审中-公开

    公开(公告)号：US20200265218A1

    公开(公告)日：2020-08-20

    申请号：US16280760

    申请日：2019-02-20

    申请人： Peng Dai ,  Juwei Lu ,  Bharath Sekar ,  Wei Li ,  Jianpeng Xu ,  Ruiwen Li

    发明人： Peng Dai ,  Juwei Lu ,  Bharath Sekar ,  Wei Li ,  Jianpeng Xu ,  Ruiwen Li

    IPC分类号： G06K9/00 ,  G06K9/62 ,  G06F16/75 ,  G06N20/00

    摘要： System and method for classifying data objects occurring in an unstructured dataset, comprising: extracting feature vectors from the unstructured dataset, each feature vector representing an occurrence of a data object in the unstructured dataset; classifying the feature vectors into feature vector sets that each correspond to a respective object class from a plurality of object classes; for each feature vector set: performing multiple iterations of a clustering operation, each iteration including clustering feature vectors from the feature vector set into clusters of similar feature vectors and identifying outlier feature vectors, wherein for at least one iteration after a first iteration of the clustering operation, outlier feature vectors identified in a previous iteration are excluded from the clustering operation; and outputting a key cluster for the feature vector set from a final iteration of the multiple iterations, the key cluster including a greater number of similar feature vectors than any of the other clusters of the final iteration; and assembling a dataset that includes at least the feature vectors from the key clusters of the feature vector sets.

    Pairwise feature learning with boosting for use in face detection
    8.
    发明授权
    Pairwise feature learning with boosting for use in face detection 有权
    配对功能学习与增强用于面部检测

    公开(公告)号：US07844085B2

    公开(公告)日：2010-11-30

    申请号：US11759460

    申请日：2007-06-07

    申请人： Juwei Lu ,  Hui Zhou

    发明人： Juwei Lu ,  Hui Zhou

    IPC分类号： G06K9/00

    CPC分类号： G06K9/00228 ,  G06K9/6257

    摘要： Systems and methods for training an AdaBoost based classifier for detecting symmetric objects, such as human faces, in a digital image. In one example embodiment, such a method includes first selecting a sub-window of a digital image. Next, the AdaBoost based classifier extracts multiple sets of two symmetric scalar features from the sub-window, one being in the right half side and one being in the left half side of the sub-window. Then, the AdaBoost based classifier minimizes the joint error of the two symmetric features for each set of two symmetric scalar features. Next, the AdaBoost based classifier selects one of the features from the set of two symmetric scalar features for each set of two symmetric scalar features. Finally, the AdaBoost based classifier linearly combines multiple weak classifiers, each of which corresponds to one of the selected features, into a stronger classifier.

    摘要翻译： 用于训练基于AdaBoost的分类器的系统和方法，用于在数字图像中检测对象对象（例如人脸）。 在一个示例实施例中，这种方法包括首先选择数字图像的子窗口。 接下来，基于AdaBoost的分类器从子窗口中提取多组两个对称标量特征，一组位于子窗口的右半边，一个位于子窗口的左半边。 然后，基于AdaBoost的分类器最小化两组对称标量特征的两个对称特征的联合误差。 接下来，基于AdaBoost的分类器从两组对称标量特征中选择两个对称标量特征集合中的一个特征。 最后，基于AdaBoost的分类器将多个弱分类器线性组合，每个弱分类器对应于所选特征之一，成为更强的分类器。

    Adaptive scanning for performance enhancement in image detection systems
    9.
    发明授权
    Adaptive scanning for performance enhancement in image detection systems 有权
    自适应扫描图像检测系统中的性能增强

    公开(公告)号：US07840037B2

    公开(公告)日：2010-11-23

    申请号：US11684478

    申请日：2007-03-09

    申请人： Juwei Lu ,  Hui Zhou ,  Mohanaraj Thiyagarajah

    发明人： Juwei Lu ,  Hui Zhou ,  Mohanaraj Thiyagarajah

    IPC分类号： G06K9/00 ,  G06K9/48 ,  G06K9/68 ,  G06K9/70

    CPC分类号： G06K9/00234 ,  G06K9/00248

    摘要： A method and system for efficiently detecting faces within a digital image. One example method includes identifying a digital image comprised of a plurality of sub-windows and performing a first scan of the digital image using a coarse detection level to eliminate the sub-windows that have a low likelihood of representing a face. The subset of the sub-windows that were not eliminated during the first scan are then scanned a second time using a fine detection level having a higher accuracy level than the coarse detection level used during the first scan to identify sub-windows having a high likelihood of representing a face.

    摘要翻译： 一种用于有效检测数字图像内的面部的方法和系统。 一个示例性方法包括识别由多个子窗口组成的数字图像，并使用粗略检测水平执行数字图像的第一次扫描，以消除具有低的表示脸部可能性的子窗口。 然后使用具有比在第一次扫描期间使用的粗略检测级别更高的精度水平的精细检测级别来第二次扫描在第一次扫描期间未被消除的子窗口的子集，以识别具有高似然性的子窗口 代表一个脸。