论文标题
视觉变压器的最新进展：最近工作的调查和前景
Recent Advances in Vision Transformer: A Survey and Outlook of Recent Work
论文作者
论文摘要
与卷积神经网络（CNN）相比，视觉变压器（VIT）正在变得越来越流行和主导技术。作为计算机视觉中苛刻的技术，VIT已成功地解决了各种视觉问题，同时着眼于远程关系。在本文中，我们首先介绍自我注意机制的基本概念和背景。接下来，我们将全面概述近期表现最好的VIT方法，这些方法在实力和弱点，计算成本以及培训和测试数据集方面进行了描述。我们彻底比较了流行的基准数据集上各种VIT算法和大多数代表性CNN方法的性能。最后，我们通过有见地的观察来探索一些局限性，并提供进一步的研究方向。项目页面以及论文集，请访问https://github.com/khawar512/vit-survey
Vision Transformers (ViTs) are becoming more popular and dominating technique for various vision tasks, compare to Convolutional Neural Networks (CNNs). As a demanding technique in computer vision, ViTs have been successfully solved various vision problems while focusing on long-range relationships. In this paper, we begin by introducing the fundamental concepts and background of the self-attention mechanism. Next, we provide a comprehensive overview of recent top-performing ViT methods describing in terms of strength and weakness, computational cost as well as training and testing dataset. We thoroughly compare the performance of various ViT algorithms and most representative CNN methods on popular benchmark datasets. Finally, we explore some limitations with insightful observations and provide further research direction. The project page along with the collections of papers are available at https://github.com/khawar512/ViT-Survey
