arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.12944cs.CV
收藏

Transformers满足视觉学习理解:综合评述

Transformers Meet Visual Learning Understanding: A Comprehensive Review

Xidian University(西安电子科技大学)

Yuting Yang, Licheng Jiao, Xu Liu, Fang Liu, Shuyuan Yang, Zhixi Feng, Xu Tang

摘要:

动态注意力机制和全局建模能力使Transformer表现出较强的特征学习能力。近年来,Transformer已成为计算机视觉中的CNN方法。本文主要综述了Transformer在图像和视频应用中的研究进展,对Transformer在视觉学习理解中的应用进行了全面的综述。首先,回顾了《Transformer》中的注意力机制。然后介绍了可视化的Transformer模型和各个模块的工作原理。第三,研究了现有的基于transformer的模型,并比较了它们在视觉学习理解应用中的性能。研究了计算机视觉的三种图像任务和两种视频任务。前者主要包括图像分类、目标检测和图像分割。后者包括对象跟踪和视频分类。这对于在多个公共基准数据集上比较不同模型在不同任务中的性能具有重要意义。最后,总结了目前存在的十个问题,并对可视化Transformer的发展前景进行了展望。

英文摘要:

Dynamic attention mechanism and global modeling ability make Transformer show strong feature learning ability. In recent years, Transformer has become comparable to CNNs methods in computer vision. This review mainly investigates the current research progress of Transformer in image and video applications, which makes a comprehensive overview of Transformer in visual learning understanding. First, the attention mechanism is reviewed, which plays an essential part in Transformer. And then, the visual Transformer model and the principle of each module are introduced. Thirdly, the existing Transformer-based models are investigated, and their performance is compared in visual learning understanding applications. Three image tasks and two video tasks of computer vision are investigated. The former mainly includes image classification, object detection, and image segmentation. The latter contains object tracking and video classification. It is significant for comparing different models' performance in various tasks on several public benchmark data sets. Finally, ten general problems are summarized, and the developing prospects of the visual Transformer are given in this review.

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。

↑