Neural networks for object detection in images are used with a spatial pyramid pooling (SPP) layer. Using the SPP network structure, a fixed-length representation is generated regardless of image size and scale. The feature maps are computed from the entire image once, and the features are pooled in arbitrary regions (sub-images) to generate fixed- length representations for training the detectors. Thus, repeated computation of the convolutional features is avoided while accuracy is enhanced.
申请公布号
WO2016054778(A1)
申请公布日期
2016.04.14
申请号
WO2014CN88165
申请日期
2014.10.09
申请人
MICROSOFT TECHNOLOGY LICENSING, LLC;HE, KAIMING;SUN, JIAN;ZHANG, XIANGYU