Classification device, classification method, and computer program product

A classification method comprising:

• generating pseudo data having a feature similar to a feature of training data;
• learning, by using the training data and the pseudo data, a classification model that classifies data into one of a pseudo class for classifying the pseudo data and a plurality of classification classes other than the pseudo class and that is constructed by a neural network;
• classifying, by using the classification model, input data as a target for classification into one of the pseudo class and the plurality of classification classes;
• and
• outputting information indicating that the input data classified into the pseudo class is data not belonging any of the plurality of classification classes.

A computer program product having a non-transitory computer readable medium including programmed instructions, wherein the instructions, when executed by a computer, cause the computer to:

• generating pseudo data having a feature similar to a feature of training data;
• learning, by using the training data and the pseudo data, a classification model that classifies data into one of a pseudo class for classifying the pseudo data and a plurality of classification classes other than the pseudo class and that is constructed by a neural network;
• classifying, by using the classification model, input data as a target for classification into one of the pseudo class and the plurality of classification classes;
• and
• outputting information indicating that the input data classified into the pseudo class is data not belonging to any of the plurality of classification classes.