Information processing method and information processing apparatus

An information processing apparatus, comprising:

• a feature vector extractor configured to input a plurality of samples to a classifier respectively, to extract a feature vector representing a feature of each sample;
• and
• a parameter updater configured to, update parameters of the classifier by minimizing a loss function for the plurality of samples, where the loss function is in positive correlation with an intra-class distance for representing a distance between feature vectors of the samples belonging to a same class, and is in negative correlation with an inter-class distance for representing the distance between the feature vectors of the samples belonging to different classes, where the intra-class distance of each sample of the plurality of samples is less than a first threshold, the inter-class distance between two different classes is greater than a second threshold, and the second threshold is greater than twice the first threshold.

A non-transitory computer-readable recording medium recording thereon instructions that, when executed, cause a computer to:

• input a plurality of samples to a classifier respectively, to extract a feature vector representing a feature of each sample;
• and
• update parameters of the classifier by minimizing a loss function for the plurality of samples, where the loss function is in positive correlation with an intra-class distance for representing a distance between feature vectors of the samples belonging to a same class, and is in negative correlation with an inter-class distance for representing the distance between the feature vectors of the samples belonging to different classes, where the intra-class distance of each sample of the plurality of samples is less than a first threshold, the inter-class distance between two different classes is greater than a second threshold, and the second threshold is greater than twice the first threshold.