Information processing apparatus and information processing method

An information processing method executed by an information processing apparatus, comprising:

• extracting features from a sample of a first class and a sample of a second class contained in a source domain, and a sample of the first class contained in a target domain, respectively, each domain containing at least one sample, each sample having a class, the second class being different from the first class;
• generating pseudo-samples of the second class in the target domain based on a distribution of samples of the first class contained in the target domain in a feature space of the extracted features;
• and
• performing data transformation in the feature space by machine learning such that a distribution of samples of the first class and samples of the second class contained in the source domain approximates a distribution of samples of the first class and the pseudo-samples of the second class contained in the target domain,
• wherein the pseudo-samples of the target domain are configured to supplement the samples of the target domain in a domain adaptation of a machine learning model from the source domain to the target domain,
• estimating a first confidence score of the distribution of samples of the first class contained in the target domain in the feature space, and generating the pseudo-samples based on a gradient of the estimated first confidence score,
• estimating a second confidence score of the distribution of samples of the second class contained in the source domain in the feature space, and generating the pseudo-samples based on a gradient of the estimated second confidence score, and
• combining the first confidence score and the second confidence score, and resampling the generated pseudo-samples based on a combined confidence score so as to distribute the resampled pseudo-samples in a region having a higher combined confidence score in the feature space.

A non-transitory machine-readable storage medium containing instructions that, when executed, cause a processor of a programmable device to perform operations comprising:

• a feature extraction process for extracting features from a sample of a first class and a sample of a second class contained in a source domain, and a sample of the first class contained in a target domain, respectively, each domain containing at least one sample, each sample having a class, the second class being different from the first class;
• a pseudo-sample generation process for generating pseudo-samples of the second class in the target domain based on a distribution of samples of the first class contained in the target domain in a feature space of the features extracted by the feature extraction process;
• and
• a data transformation process for performing data transformation in the feature space by machine learning such that a distribution of samples of the first class and samples of the second class contained in the source domain approximates a distribution of samples of the first class and the pseudo-samples of the second class contained in the target domain,
• wherein the pseudo-samples of the target domain are configured to supplement the samples of the target domain in a domain adaptation of a machine learning model from the source domain to the target domain,
• a first confidence score estimation process for estimating a first confidence score of the distribution of samples of the first class contained in the target domain in the feature space, and for generating the pseudo-samples based on a gradient of the estimated first confidence score,
• a second confidence score estimation process for estimating a second confidence score of the distribution of samples of the second class contained in the source domain in the feature space, and for generating the pseudo-samples based on a gradient of the estimated second confidence score, and
• a combination process for combining the first confidence score and the second confidence score, and for resampling the generated pseudo-samples based on a combined confidence score so as to distribute the resampled pseudo-samples in a region having a higher combined confidence score in the feature space.