FDViT: Improve the Hierarchical Architecture of Vision Transformer

Despite the fact that transformer-based models have yielded great success in computer vision tasks, they suffer from the challenge of high computational costs that limits their use on resource-constrained devices. One major reason is that vision transformers have redundant calculations since the self-attention operation generates patches with high similarity at a later stage in the network. Hierarchical architectures have been proposed for vision transformers to alleviate this challenge. However, by shrinking the spatial dimensions to half of the originals with downsampling layers, the challenge is actually overcompensated, as too much information is lost. In this paper, we propose FDViT to improve the hierarchical architecture of the vision transformer by using a flexible downsampling layer that is not limited to integer stride to smoothly reduce the sizes of the middle feature maps. Furthermore, a masked auto-encoder architecture is used to facilitate the training of the proposed flexible downsampling layer and produces informative outputs. Experimental results on benchmark datasets demonstrate that the proposed method can reduce computational costs while increasing classification performance and achieving state-of-the-art results. For example, the proposed FDViT-S model achieves a top-1 accuracy of 81.5%, which is 1.7 percent points higher than the ViT-S model and reduces 39% FLOPs.