arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.15490cs.LGcs.NE
收藏

深度学习中卷积的全面综述:应用、挑战与未来趋势

A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends

Sharif University of Technology(谢里夫理工大学);New York University (NYU) Abu Dhabi(纽约大学阿布扎比分校);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)

Abolfazl Younesi, Mohsen Ansari, MohammadAmin Fazli, Alireza Ejlali, Muhammad Shafique, Jörg Henkel

AI总结:

该综述系统比较 1D/2D/3D CNN 及多种卷积与 NAS 架构,梳理其性能、应用、平台框架、挑战及 6D 视觉等未来方向。

摘要:

在当今数字时代,卷积神经网络(Convolutional Neural Networks,CNNs)作为深度学习(Deep Learning,DL)的一个子集,被广泛用于图像分类、目标检测和图像分割等各类计算机视觉任务。为满足特定需求和要求,人们设计了众多类型的 CNN,包括 1D、2D 和 3D CNN,以及空洞卷积、分组卷积、注意力卷积、深度卷积和 NAS 等。每种类型的 CNN 都有其独特的结构和特征,因而适用于特定任务。为理解这些不同 CNN 类型的优势与弱点,对其进行透彻理解和比较分析至关重要。此外,研究每类 CNN 的性能、局限性和实际应用,有助于未来开发新的、改进的架构。我们还从多个角度深入探讨研究人员用于研究或开发的平台和框架。另外,我们探索了 CNN 的主要研究领域,如 6D 视觉、生成模型和元学习。本综述对各种 CNN 架构进行了全面考察和比较,突出其架构差异,并强调各自的优点、缺点、应用、挑战和未来趋势。

英文摘要:

In today's digital age, Convolutional Neural Networks (CNNs), a subset of Deep Learning (DL), are widely used for various computer vision tasks such as image classification, object detection, and image segmentation. There are numerous types of CNNs designed to meet specific needs and requirements, including 1D, 2D, and 3D CNNs, as well as dilated, grouped, attention, depthwise convolutions, and NAS, among others. Each type of CNN has its unique structure and characteristics, making it suitable for specific tasks. It's crucial to gain a thorough understanding and perform a comparative analysis of these different CNN types to understand their strengths and weaknesses. Furthermore, studying the performance, limitations, and practical applications of each type of CNN can aid in the development of new and improved architectures in the future. We also dive into the platforms and frameworks that researchers utilize for their research or development from various perspectives. Additionally, we explore the main research fields of CNN like 6D vision, generative models, and meta-learning. This survey paper provides a comprehensive examination and comparison of various CNN architectures, highlighting their architectural differences and emphasizing their respective advantages, disadvantages, applications, challenges, and future trends.

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。

↑