首页>
外国专利>
IMAGE FEATURE LEARNING DEVICE, IMAGE FEATURE LEARNING METHOD, IMAGE FEATURE EXTRACTION DEVICE, IMAGE FEATURE EXTRACTION METHOD, AND PROGRAM
IMAGE FEATURE LEARNING DEVICE, IMAGE FEATURE LEARNING METHOD, IMAGE FEATURE EXTRACTION DEVICE, IMAGE FEATURE EXTRACTION METHOD, AND PROGRAM
展开▼
机译:图像特征学习装置,图像特征学习方法,图像特征提取装置,图像特征提取方法以及程序
展开▼
页面导航
摘要
著录项
相似文献
摘要
The purpose of the present invention is to enable learning of a neural network for extracting features of images having high robustness from an undiscriminating image region while minimizing the number of parameters of a pooling layer. A parameter learning unit 130 learns parameters of each layer in a convolutional neural network formed by including a fully convolution layer for performing convolution of an input image to output a feature tensor of the input image, a weighting matrix estimation layer for estimating a weighting matrix indicating a weighting of each element of the feature tensor, and a pooling layer for extracting a feature vector of the input image on the basis of the feature tensor and the weighting matrix. The parameter learning unit 130 learns the parameters such that a loss function value obtained by calculating a loss function expressed by using a distance between a first feature vector of a first image and a second feature vector of a second image which are relevant images and are obtained by applying the convolutional neural network.
展开▼