# A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation Source: [A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:37:22.464Z Authors: Wuyang Chen, Xianzhi Du, Fan Yang, Lucas Beyer, Xiaohua Zhai, Tsung-Yi Lin, Huizhong Chen, Jing Li, Xiaodan Song, Zhangyang Wang, Denny Zhou Published: 2021-12-17T20:11:56.000Z ## Abstract This work presents a simple vision transformer design as a strong baseline for object localization and instance segmentation tasks. Transformers recently demonstrate competitive performance in image classification tasks. To adopt ViT to object detection and dense prediction tasks, many works inherit the multistage design from convolutional networks and highly customized ViT architectures. Behind this design, the goal is to pursue a better trade-off between computational cost and effective aggregation of multiscale global contexts. However, existing works adopt the multistage architectural design as a black-box solution without a clear understanding of its true benefits. In this paper, we comprehensively study three architecture design choices on ViT -- spatial reduction, doubled channels, and multiscale features -- and demonstrate that a vanilla ViT architecture can fulfill this goal without handcrafting multiscale features, maintaining the original ViT design philosophy. We further complete a scaling rule to optimize our model's trade-off on accuracy and computation cost / model size. By leveraging a constant feature resolution and hidden size throughout the encoder blocks, we propose a simple and compact ViT architecture called Universal Vision Transformer (UViT) that achieves strong performance on COCO object detection and instance segmentation tasks. ## 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. - [Object Detection on COCO 2017](): Object Detection; COCO 2017; AP (Box): 52.5. - [Instance Segmentation on COCO 2017](): Instance Segmentation; COCO 2017; APm: 44.3. - [Instance Segmentation on COCO (val)](): Instance Segmentation; COCO (val); APmk: 44.8. - [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. - [Object Detection on COCO (val)](): Object Detection; COCO (val); mAP: not recorded. ## Original sources and implementation [Original paper]() [PDF]()