Learning device including a machine learning mathematical model
A learning device according to the present disclosed technology is a learning device including a coupled mathematical model capable of machine learning and learning a data set of a target domain from a data set of an original domain for a teacher, in which a pre-stage part of the coupled mathematical model generates a plurality of low-level feature maps from input image data, compares the low-level feature maps of data sets belonging to the same type of learning target for the original domain and the target domain in the image data, and calculates domain-shared features, and calculates domain relaxation learning information for each space of {1} color, {2} illumination, {3} low frequency component, and {4} high frequency component among the domain-shared features.
1 . A learning device, comprising: a coupled mathematical model configured for machine learning and learning a data set of a target domain from a data set of an original domain for a teacher image, wherein
a pre-stage part of the coupled mathematical model
generates a plurality of low-level feature maps from input image data,
compares the low-level feature maps of data sets belonging to the same type of learning target for the original domain and the target domain in the image data, calculates domain-shared features, and
calculates domain relaxation learning information for each feature space of (1) color, (2) illumination, (3) low frequency component, and (4) high frequency component among the domain-shared features, and further comprising:
a high dimension feature imparter to weight a feature map of the target domain input using the domain relaxation learning information to generate a new weighting feature map; and
a learning information corrector to switch the domain-shared features emphasized according to Epoch of main learning of an inference device.