Domain Generalisation with Bidirectional Encoder Representations from Vision Transformers
This work addresses domain generalization for computer vision applications, but it is incremental as it applies an existing method (BEIT) to new data in this context.
The paper tackled domain generalization for vision tasks by evaluating vision transformer architectures on out-of-distribution data, finding that BEIT performed best and achieved significant improvements in accuracy on benchmarks like PACS, Home-Office, and DomainNet, reducing gaps between within-distribution and OOD performance.
Domain generalisation involves pooling knowledge from source domain(s) into a single model that can generalise to unseen target domain(s). Recent research in domain generalisation has faced challenges when using deep learning models as they interact with data distributions which differ from those they are trained on. Here we perform domain generalisation on out-of-distribution (OOD) vision benchmarks using vision transformers. Initially we examine four vision transformer architectures namely ViT, LeViT, DeiT, and BEIT on out-of-distribution data. As the bidirectional encoder representation from image transformers (BEIT) architecture performs best, we use it in further experiments on three benchmarks PACS, Home-Office and DomainNet. Our results show significant improvements in validation and test accuracy and our implementation significantly overcomes gaps between within-distribution and OOD data.