Medical image segmentation is a crucial task in medical image analysis. Despite near expert-label performance with the application of the deep learning method in medical image segmentation, the generalization of such models in the clinical environment remains a significant challenge. Transfer learning from a large medical dataset from the same domain is a common technique to address generalizability. However, it is difficult to find a similar large medical dataset. To address generalizability in polyp segmentation, we have used an ensemble of four MultiResUNet architectures, each trained on the combination of the different centered datasets provided by the challenge organizers. Our method achieved a decent performance of 0.6172 ± 0.0778 for the multi-centered dataset. Our study shows that significant work needs to be done to develop a computer-aided diagnosis system to detect and localize polyp of the multi-center datasets, which is essential for improving the quality of the colonoscopy.