Abstract: A method by one or more computers for learning a machine learning model classifying an input image into known classes and an unknown class by extracting a feature of the input image. The method comprises acquiring a set of features of a plurality of samples of training data each of which is with a label, calculating a loss function based on the set of the features, and learning the machine learning model to reduce the loss function. The loss function is calculated to include a first loss function and a second loss function. The first loss function is configured to become larger as first distances become smaller than a predetermined margin. The second loss function is configured to become larger as second distances become larger and as third distances become smaller.