发明名称 |
Learning Deep Face Representation |
摘要 |
Face representation is a crucial step of face recognition systems. An optimal face representation should be discriminative, robust, compact, and very easy to implement. While numerous hand-crafted and learning-based representations have been proposed, considerable room for improvement is still present. A very easy-to-implement deep learning framework for face representation is presented. The framework bases on pyramid convolutional neural network (CNN). The pyramid CNN adopts a greedy-filter-and-down-sample operation, which enables the training procedure to be very fast and computation efficient. In addition, the structure of Pyramid CNN can naturally incorporate feature sharing across multi-scale face representations, increasing the discriminative ability of resulting representation. |
申请公布号 |
US2015347820(A1) |
申请公布日期 |
2015.12.03 |
申请号 |
US201414375679 |
申请日期 |
2014.05.27 |
申请人 |
BEIJING KUANGSHI TECHNOLOGY CO., LTD. |
发明人 |
Yin Qi;Cao Zhimin;Jiang Yuning;Fan Haoqiang |
分类号 |
G06K9/00;G06K9/66 |
主分类号 |
G06K9/00 |
代理机构 |
|
代理人 |
|
主权项 |
1. A computer-implemented method for training a pyramid convolutional neural network (CNN) comprising at least N shared layers where N≧2 and at least one unshared network coupled to the Nth shared layer, the method comprising:
training CNN levels 1 to N in that order, wherein CNN level n comprises an input for receiving face images, the first n shared layers of the pyramid CNN, the unshared network of the pyramid CNN, and an output producing representations of the face images; wherein the input is coupled to a first of the n shared layers; each shared layer includes convolution, non-linearity and down-sampling; an nth of the n shared layers is coupled to the unshared network; and the unshared network is coupled to the output; wherein training CNN level n comprises:
presenting face images to the input, each face image producing a corresponding representation at the output;processing the representations to produce estimates of a metric, for which actual values of the metric are known; andadapting the nth shared layer and the unshared network based on the estimates of the metric compared to the actual values of the metric. |
地址 |
Beijing CN |