视觉Transformer的最新进展：综述与近期工作展望
Recent Advances in Vision Transformer: A Survey and Outlook of Recent Work
AI总结：
本文综述了视觉Transformer（ViT）的最新进展，对比了其与CNN在视觉任务中的表现，分析了主流方法的优缺点、计算成本及数据集，并指出了未来研究方向。
摘要：
与卷积神经网络（CNNs）相比，视觉Transformer（ViTs）正变得越来越流行，并成为处理各种视觉任务的主导技术。作为计算机视觉中的一项重要技术，ViTs在关注长距离关系的同时，已成功解决了各种视觉问题。在本文中，我们首先介绍自注意力机制的基本概念和背景。接下来，我们全面概述了近期性能最佳的ViT方法，从优缺点、计算成本以及训练和测试数据集等方面进行描述。我们深入比较了各种ViT算法和最具代表性的CNN方法在流行基准数据集上的性能。最后，我们探讨了一些局限性，并提供了富有洞察力的观察和进一步的研究方向。项目页面及论文合集可在https://github.com/khawar512/ViT-Survey获取。
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
