Papers › Dual Vision Transformer

Dual Vision Transformer

11 Jul 2022arXiv:2207.04976archive 2025-07-28

Ting Yao, Yehao Li, Yingwei Pan, Yu Wang, Xiao-Ping Zhang, Tao Mei

Prior works have proposed several strategies to reduce the computational cost of self-attention mechanism. Many of these works consider decomposing the self-attention procedure into regional and local feature extraction procedures that each incurs a much smaller computational complexity. However, regional information is typically only achieved at the expense of undesirable information lost owing to down-sampling. In this paper, we propose a novel Transformer architecture that aims to mitigate the cost issue, named Dual Vision Transformer (Dual-ViT). The new architecture incorporates a critical semantic pathway that can more efficiently compress token vectors into global semantics with reduced order of complexity. Such compressed global semantics then serve as useful prior information in learning finer pixel level details, through another constructed pixel pathway. The semantic pathway and pixel pathway are then integrated together and are jointly trained, spreading the enhanced self-attention information in parallel through both of the pathways. Dual-ViT is henceforth able to reduce the computational complexity without compromising much accuracy. We empirically demonstrate that Dual-ViT provides superior accuracy than SOTA Transformer architectures with reduced training complexity. Source code is available at \url{https://github.com/YehLi/ImageNetModel}.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

yehli/imagenetmodel officialmentioned in paperpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer Vision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections