Information processing method and information processing apparatus

An information processing apparatus, which performs training on a classification model by using a plurality of training samples, the apparatus comprising:

• a processor coupled to a memory and to,
• adjust a distribution of feature vectors of the plurality of training samples in a feature space based on a typical sample in the plurality of training samples;
• and
• perform training on the classification model by using the adjusted feature vectors of the plurality of training samples,
• wherein,
• the typical sample is a training sample having a most typical feature of a class in the classification model, the most typical feature of the class is to cause the classification model not to classify the typical sample into another class, and
• to adjust the distribution includes causing feature vectors of other training samples other than the typical sample to aggregate towards a feature vector of the typical sample.

An information processing method by a computer, comprising:

• detecting data to be detected, by using a classification model obtained by performing training of the classification model using a plurality of training samples by,
• adjusting a distribution of feature vectors of the plurality of training samples in the feature space based on a typical sample in the plurality of training samples;
• and
• performing training on the classification model by using the adjusted feature vectors of the plurality of training samples,
• wherein
• the typical sample is a training sample having a most typical feature of a class in the classification model, the most typical feature of the class is to cause the classification model not to classify the typical sample into another class, and
• the adjusting includes causing feature vectors of other training samples other than the typical sample to aggregate towards a feature vector of the typical sample.