Learning apparatus, operation program of learning apparatus, and operation method of learning apparatus
AssigneeFUJIFILM Corporation
InventorTakashi WAKUI
Life of this patent
Estimating the term…
Abstract
A learning apparatus learns a machine learning model for performing semantic segmentation of determining a plurality of classes in an input image in units of pixels by extracting, for each layer, features which are included in the input image and have different frequency bands of spatial frequencies. A learning data analysis unit analyzes the frequency bands included in an annotation image of learning data. A learning method determination unit determines a learning method using the learning data based on an analysis result of the frequency bands by the learning data analysis unit. A learning unit learns the machine learning model via the determined learning method using the learning data.
Claims13
A learning apparatus that inputs learning data to a machine learning model including a plurality of layers for analyzing an input image and learns the machine learning model, the machine learning model being a model for performing semantic segmentation of determining a plurality of classes in the input image in units of pixels by extracting, for each layer, features which are included in the input image and have different frequency bands of spatial frequencies, the learning apparatus comprising:
- at lease one memory and at least one processor which function as:
- a learning data analysis unit that analyzes at least the frequency bands included in an annotation image of the learning data, the learning data being a pair of a learning input image and the annotation image in which each class region included in the learning input image is indicated by an annotation;
- a learning method determination unit that determines a learning method using the learning data based on an analysis result of the frequency bands by the learning data analysis unit;
- and
- a learning unit that learns the machine learning model via the determined learning method using the learning data.
A non-transitory computer-readable storage medium storing an operation program of a learning apparatus that inputs learning data to a machine learning model including a plurality of layers for analyzing an input image and learns the machine learning model, the machine learning model being a model for performing semantic segmentation of determining a plurality of classes in the input image in units of pixels by extracting, for each layer, features which are included in the input image and have different frequency bands of spatial frequencies, the operation program causing a computer to function as:
- a learning data analysis unit that analyzes at least the frequency bands included in an annotation image of the learning data, the learning data being a pair of a learning input image and the annotation image in which each class region included in the learning input image is indicated by an annotation;
- a learning method determination unit that determines a learning method using the learning data based on an analysis result of the frequency bands by the learning data analysis unit;
- and
- a learning unit that learns the machine learning model via the determined learning method using the learning data.
An operation method of a learning apparatus that inputs learning data to a machine learning model including a plurality of layers for analyzing an input image and learns the machine learning model, the machine learning model being a model for performing semantic segmentation of determining a plurality of classes in the input image in units of pixels by extracting, for each layer, features which are included in the input image and have different frequency bands of spatial frequencies, the operation method comprising:
- a learning data analysis step of analyzing at least the frequency bands included in an annotation image of the learning data, the learning data being a pair of a learning input image and the annotation image in which each class region included in the learning input image is indicated by an annotation;
- a learning method determination step of determining a learning method using the learning data based on an analysis result of the frequency bands in the learning data analysis step;
- and
- a learning step of learning the machine learning model via the determined learning method using the learning data.
Dependencies are inferred from the claim text.