Method for generating objective function, apparatus, electronic device and computer readable medium
OwnerYi He, Changhu Wanginventors
Life of this patent
Estimating the term…
Abstract
A method for generating a target function is provided. The method includes: performing normalization processing on a vector corresponding to each pixel in a target feature map set to generate a target vector, so as to obtain a target vector set; generating hash coding corresponding to each vector in the target vector set, to obtain a hash coding set; determining a prior probability of each hash coding in the hash coding set; and generating a target function based on an entropy of the prior probability.
Claims11
A method for generating a target function comprising:
- performing normalization processing on a vector corresponding to each pixel in a target contour feature map set to generate a target vector, so as to obtain a target vector set, wherein the target contour feature map set is obtained by extracting features of a target image set over a feature extraction network;
- generating hash coding corresponding to each vector in the target vector set, to obtain a uniform hash coding set;
- determining a prior probability of each hash coding in the uniform hash coding set;
- generating a target function based on an entropy of the prior probability, the prior probability represents distribution of image features;
- and
- optimizing the feature extraction network based on the target function to obtain a trained feature extraction network.
An apparatus for training a feature extraction network comprising:
- at least one processor;
- and
- at least one memory communicatively coupled to the at least one processor and storing instructions that upon execution by the at least one processor cause the apparatus to:
- perform normalization processing on a vector corresponding to each pixel in a target contour feature map set to generate a target vector, to obtain a target vector set, wherein the target contour feature map set is obtained by extracting features of a target image set over the feature extraction network;
- generate hash coding corresponding to each vector in the target vector set, to obtain a uniform hash coding set;
- determine a prior probability of each hash coding in the uniform hash coding set;
- generate a target function based on an entropy of the prior probability, the prior probability represents distribution of image features;
- and
- optimize the feature extraction network based on the target function to obtain a trained feature extraction network.
A computer readable non-transitory storage medium,
- bearing computer-readable instructions that upon execution on a computing device cause the computing device at least to:
- perform normalization processing on a vector corresponding to each pixel in a target contour feature map set to generate a target vector, to obtain a target vector set, wherein the target contour feature map set is obtained by extracting features of a target image set over a feature extraction network;
- generate hash coding corresponding to each vector in the target vector set, to obtain a uniform hash coding set;
- determine a prior probability of each hash coding in the uniform hash coding set;
- generate a target function based on an entropy of the prior probability, the prior probability represents distribution of image features;
- and
- optimize the feature extraction network based on the target function to obtain a trained feature extraction network.
Dependencies are inferred from the claim text.