| 发明名称 |
UNIVERSAL CORRESPONDENCE NETWORK |
| 摘要 |
A computer-implemented method for training a convolutional neural network (CNN) is presented. The method includes extracting coordinates of corresponding points in the first and second locations, identifying positive points in the first and second locations, identifying negative points in the first and second locations, training features that correspond to positive points of the first and second locations to move closer to each other, and training features that correspond to negative points in the first and second locations to move away from each other. |
| 申请公布号 |
US2017124711(A1) |
申请公布日期 |
2017.05.04 |
| 申请号 |
US201615342700 |
申请日期 |
2016.11.03 |
| 申请人 |
NEC Laboratories America, Inc. |
发明人 |
Chandraker Manmohan;Choy Christopher Bongsoo;Savarese Silvio |
| 分类号 |
G06T7/00;G06K9/42;G06N3/08;G06K9/46 |
主分类号 |
G06T7/00 |
| 代理机构 |
|
代理人 |
|
| 主权项 |
1. A computer-implemented method for training a convolutional neural network (CNN), the method comprising:
extracting coordinates of corresponding points in first and second locations; identifying positive points in the first and second locations; identifying negative points in the first and second locations; training features that correspond to positive points of the first and second locations to move closer to each other; and training features that correspond to negative points in the first and second locations to move away from each other. |
| 地址 |
Princeton NJ US |
