公开(公告)号：EP3218890A1

公开(公告)日：2017-09-20

申请号：EP15858182.7

申请日：2015-10-16

申请人： NEC Laboratories America, Inc.

发明人： YANG, Tianbao ,  WANG, Xiaoyu ,  LIN, Yuanqing ,  XIE, Saining

IPC分类号： G09B5/00 ,  G09B25/02

CPC分类号： G06N3/08 ,  G06N3/0454 ,  G06N3/084

摘要： Systems and methods are disclosed for training a learning machine by augmenting data from fine-grained image recognition with labeled data annotated by one or more hyper-classes, performing multi-task deep learning; allowing fine-grained classification and hyper-class classification to share and learn the same feature layers; and applying regularization in the multi-task deep learning to exploit one or more relationships between the fine-grained classes and the hyper-classes.

摘要翻译： 公开了系统和方法，用于通过利用由一个或多个超级类别注释的标记数据来增强来自细粒度图像识别的数据来训练学习机器，执行多任务深度学习; 允许细粒度分类和超类分类共享和学习相同的要素图层; 并在多任务深度学习中应用正则化来利用细粒度类和超类之间的一个或多个关系。