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

本文介绍了近期表现最佳的 Vision Transformers 方法，对其强弱项、计算成本、训练和测试数据集进行了全面综述，并在流行基准数据集上与各种 ViT 算法以及代表性 CNN 方法的性能进行了充分比较，最后讨论了一些局限性和提出了未来研究方向。

视觉Transformer的最新进展：近期研究的综述和展望