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.
FPGA-based Acceleration for Convolutional Neural Networks: A Comprehensive Review
Key Laboratory of Low-Dimensional Quantum Structures and Quantum Control of Ministry of Education, School of Physics and Electronics, Hunan Normal University(教育部低维量子结构与量子控制重点实验室,物理电子学院,湖南师范大学)
A Survey on Evolutionary Computation for Computer Vision and Image Analysis: Past, Present, and Future Trends
Zhengzhou University(郑州大学);Victoria University of Wellington(惠灵顿维多利亚大学);University of Granada(格拉纳达大学);Andalusian Research Institute in Artificial Intelligence(安达卢西亚人工智能研究所);Panacea Cooperative Research S.Coop.(Panacea合作研究合作社);University of Parma(帕尔马大学)
A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference
MindGarage(思维车库);Technical University Kaiserslautern(凯泽斯劳滕工业大学);NeuralSpace(神经空间);Imperial College London(帝国理工学院);Luleå University of Technology(吕勒奥理工大学)
人工神经网络是连接主义系统,它通过对示例的学习来执行给定的任务,而不需要关于任务的先验知识。这是通过为每个节点中的权重找到最佳点估计来完成的。通常,使用点估计作为权重的网络在大数据集上表现良好,但它们无法表达数据很少或没有数据的区域的不确定性,导致过度自信的决策。本文提出了一种基于变分推理的贝叶斯卷积神经网络(BayesCNN),它引入了权值的概率分布。此外,提出的贝叶斯CNN架构适用于图像分类,图像超分辨率和生成对抗网络等任务。将结果与MNIST、CIFAR-10和CIFAR-100数据集上的基于点估计的体系结构进行比较,用于图像分类任务,用于图像超分辨率任务的BSD 300数据集和用于生成对抗网络任务的CIFAR 10数据集。BayesCNN是基于Bayes by Backprop的,它导出了真实后验的变分近似。因此,我们引入了应用两个卷积运算的想法,一个用于均值,一个用于方差。我们所提出的方法不仅实现了性能等同于频率论推理在相同的架构,但也纳入了测量的不确定性和正规化。它进一步消除了在模型中使用dropout。此外,我们预测了模型预测基于认知和任意不确定性的确定性,并通过经验展示了不确定性如何降低,从而使网络做出的决策随着训练精度的提高而变得更加确定。最后,我们提出了修剪贝叶斯架构,使其更具计算性和时间效率的方法。
Exploring the Role of Convolutional Neural Networks (CNN) in Dental Radiography Segmentation: A Comprehensive Systematic Literature Review
Research Groups in Intelligent Machines (REGIM Lab), University of Sfax, National Engineering School of Sfax (ENIS)(智能机器研究组(REGIM实验室),斯法克斯大学,斯法克斯国家工程学院)
A Comprehensive Study of Data Augmentation Strategies for Prostate Cancer Detection in Diffusion-weighted MRI using Convolutional Neural Networks
University of Electronic Science and Technology of China(电子科技大学);University of Toronto(多伦多大学);The Hospital for Sick Children (SickKids)(SickKids 儿童医院(病童医院));Sinai Health System(西奈卫生系统);University Health Network(大学健康网络);Lunenfeld-Tanenbaum Research Institute(卢嫩菲尔德-塔南鲍姆研究所);Sunnybrook Research Institute(桑尼布鲁克研究所)
Comprehensive Analysis of Network Robustness Evaluation Based on Convolutional Neural Networks with Spatial Pyramid Pooling
School of Systems Science and Engineering, Sun Yat-sen University(中山大学系统科学与工程学院);School of Cyber Science and Technology, University of Science and Technology of China(中国科学技术大学网络空间安全学院)