# Beyond Fixation: Dynamic Window Visual Transformer Source: [Beyond Fixation: Dynamic Window Visual Transformer]() Collection index: [llms.txt]() Data updated: 2026-01-04T05:12:28.499Z Authors: Pengzhen Ren, Changlin Li, Guangrun Wang, Yun Xiao, Qing Du, Xiaodan Liang, Xiaojun Chang Published: 2022-03-24T05:38:07.000Z ## Abstract Recently, a surge of interest in visual transformers is to reduce the computational cost by limiting the calculation of self-attention to a local window. Most current work uses a fixed single-scale window for modeling by default, ignoring the impact of window size on model performance. However, this may limit the modeling potential of these window-based models for multi-scale information. In this paper, we propose a novel method, named Dynamic Window Vision Transformer (DW-ViT). The dynamic window strategy proposed by DW-ViT goes beyond the model that employs a fixed single window setting. To the best of our knowledge, we are the first to use dynamic multi-scale windows to explore the upper limit of the effect of window settings on model performance. In DW-ViT, multi-scale information is obtained by assigning windows of different sizes to different head groups of window multi-head self-attention. Then, the information is dynamically fused by assigning different weights to the multi-scale window branches. We conducted a detailed performance evaluation on three datasets, ImageNet-1K, ADE20K, and COCO. Compared with related state-of-the-art (SoTA) methods, DW-ViT obtains the best performance. Specifically, compared with the current SoTA Swin Transformers \\cite{liu2021swin}, DW-ViT has achieved consistent and substantial improvements on all three datasets with similar parameters and computational costs. In addition, DW-ViT exhibits good scalability and can be easily inserted into any window-based visual transformers. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on ImageNet 1k (test)](): Image Classification; ImageNet 1k (test); Top-1 Accuracy: 83.8. - [Semantic Segmentation on ADE20K (val)](): Semantic segmentation; ADE20K (val); mIoU: 48.7. - [Object Detection on COCO 2017 (val)](): Object Detection; COCO 2017 (val); AP: not recorded. - [Instance Segmentation on COCO 2017 (val)](): Instance Segmentation; COCO 2017 (val); APm: not recorded. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()