CbDA: Contrastive-Based Data Augmentation for Domain Generalization

In the realm of domain generalization (DG), domain adversarial training is a popular method for achieving invariant representations and is often applied to various tasks in this field. Notably, recent developments in supervised learning, particularly in classification, have shown that methods converging toward smoother optima yield better generalization. This research delves into the impact of contrastive-based data augmentation on DG, focusing on leveraging category-specific distribution statistics. We introduce an innovative contrastive loss at the sample level, tailored to align samplewise representations with semantic distributions across domains. This involves encouraging representations within the same category to form clusters while ensuring those from different categories remain distinct, thus enhancing the model’s classification strength. Additionally, we establish an upper limit for this loss function. This approach efficiently handles an infinite array of both similar and dissimilar sample pairs. Our methodology significantly surpasses the baseline model, a fact underscored by comprehensive empirical evaluations on challenging benchmarks such as Digits-DG, PACS, Office–Home, and DomainNet.