Domain generalization by class-aware negative sampling-based contrastive learning

When faced with the issue of different feature distribution between training and test data, the test data may differ in style and background from the training data due to the collection sources or privacy protection. That is, the transfer generalization problem. Contrastive learning, which is currently the most successful unsupervised learning method, provides good generalization performance for the various distributions of data and can use labeled data more effectively without overfitting. This study demonstrates how contrast can enhance a model’s ability to generalize, how joint contrastive learning and supervised learning can strengthen one another, and how this approach can be broadly used in various disciplines.