The classification of gastric mucosal inflammation (IM) is a critical task in gastroenterology, as accurate identification of gastric conditions is essential for diagnosis and treatment. However, medical imaging data often exhibit significant variability due to differences in image quality, equipment used, and clinical practices across datasets. This variability presents a challenge for developing models that can generalize well across different clinical environments, making it difficult to apply models trained in one domain to another without significant performance degradation. Domain adaptation (DA) provides a solution to this challenge by allowing models to adapt to new domains without requiring labeled data from the target domain.