# Vision Transformers: State of the Art and Research Challenges

Source: [Vision Transformers: State of the Art and Research Challenges](<https://www.sota2.com/research/paper/68fa6cf11e209131cea36b3b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:21:36.840Z

Authors: Bo-Kai Ruan, Hong-Han Shuai, Wen-Huang Cheng

Published: 2022-07-07T02:01:56.000Z

## Abstract

Transformers have achieved great success in natural language processing. Due to the powerful capability of self-attention mechanism in transformers, researchers develop the vision transformers for a variety of computer vision tasks, such as image recognition, object detection, image segmentation, pose estimation, and 3D reconstruction. This paper presents a comprehensive overview of the literature on different architecture designs and training tricks (including self-supervised learning) for vision transformers. Our goal is to provide a systematic review with the open research opportunities.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2207.03041>)

[PDF](<https://arxiv.org/pdf/2207.03041.pdf>)
