arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.01232cs.CVcs.AI
收藏

图像分类任务中 Vision Transformers 的综合研究

A Comprehensive Study of Vision Transformers in Image Classification Tasks

University of Windsor(温莎大学)

Mahmoud Khalil, Ahmad Khalil, Alioune Ngom

AI总结:

本文综述 Vision Transformers 在图像分类中的发展,梳理相关数据集、模型演进及注意力机制,并指出开放问题与未来研究方向。

摘要:

图像分类是计算机视觉领域的一项基础任务,常被用作衡量计算机视觉进展的基准。过去几年,由于深度学习的出现,图像分类取得了重大进展。然而,挑战仍然存在,例如对细粒度视觉信息进行建模、高昂的计算成本、模型的并行性,以及各数据集之间不一致的评估协议。本文中,我们对现有关于将 Vision Transformers 用于图像分类的论文进行了全面综述。我们首先介绍了影响模型设计的流行图像分类数据集。随后,我们按时间顺序展示 Vision Transformers 模型,从将注意力机制适配到视觉任务的早期尝试开始,接着介绍 Vision Transformers 的采用,因为它们已被证明能够成功捕获图像内的复杂模式和长程依赖。最后,我们讨论尚未解决的问题,并阐明图像分类领域的机遇,以促进新的研究思路。

英文摘要:

Image Classification is a fundamental task in the field of computer vision that frequently serves as a benchmark for gauging advancements in Computer Vision. Over the past few years, significant progress has been made in image classification due to the emergence of deep learning. However, challenges still exist, such as modeling fine-grained visual information, high computation costs, the parallelism of the model, and inconsistent evaluation protocols across datasets. In this paper, we conduct a comprehensive survey of existing papers on Vision Transformers for image classification. We first introduce the popular image classification datasets that influenced the design of models. Then, we present Vision Transformers models in chronological order, starting with early attempts at adapting attention mechanism to vision tasks followed by the adoption of vision transformers, as they have demonstrated success in capturing intricate patterns and long-range dependencies within images. Finally, we discuss open problems and shed light on opportunities for image classification to facilitate new research ideas.

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。

↑