This study aims to improve the performance of event classification in collider physics by introducing a foundation model based on deep learning. Event classification is a typical problem in collider physics, where the goal is to distinguish the signal events from the background events as much as possible in order to search for new phenomena in nature. A foundation model refers to a pre-trained model, which is usually trained on a large amount of unlabelled data, and then transferred to downstream tasks and fine-tuned. In applying this foundation model concept to collider physics, the following novelties are introduced in this study. First, the real particle collision data collected by the CMS experiment are used to train the foundation model. A self-supervised learning technique is introduced to process this unlabelled data. Second, data augmentation techniques based on physics knowledge are applied during the training process of the foundation model. This paper describes details of the self-supervised learning and data augmentation techniques used in this study, and shows the performance improvement in event classification by introducing this foundation model.