A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects

By Zewen Li, Fan Liu, Wenjie Yang, Shouheng Peng, Jun Zhou. 2020

4,320 citations recorded by the source corpus.

A convolutional neural network (CNN) is one of the most significant networks in the deep learning field. Since CNN made impressive achievements in many areas, including but not limited to computer vision and natural language processing, it attracted much attention from both industry and academia in the past few years. The existing reviews mainly focus on CNN’s applications in different scenarios without considering CNN from a general perspective, and some novel ideas proposed recently are not covered. In this review, we aim to provide some novel ideas and prospects in this fast-growing field. Besides, not only 2-D convolution but also 1-D and multidimensional ones are involved. First, this review introduces the history of CNN. Second, we provide an overview of various convolutions. Third, some classic and advanced CNN models are introduced; especially those key points making them reach state-of-the-art results. Fourth, through experimental analysis, we draw some conclusions and provide several rules of thumb for functions and hyperparameter selection. Fifth, the applications of 1-D, 2-D, and multidimensional convolution are covered. Finally, some open issues and promising directions for CNN are discussed as guidelines for future work.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Hongsheng Li
2. Xiaogang Wang
3. Jifeng Dai
4. Xizhou Zhu
5. Xinwang Liu
6. Yue Liu
7. Siwei Wang
8. Lingyuan Meng

In Computer Vision and Pattern Recognition

1. Xiaogang Wang
2. Hongsheng Li
3. Luc Van Gool
4. Dacheng Tao
5. Andrea Vedaldi
6. Yi Yang
7. Yu Qiao
8. Chen Change Loy

In Model Architectures

1. Xizhou Zhu
2. Xiaogang Wang
3. Jifeng Dai
4. Hongsheng Li
5. Jinguo Zhu
6. Mohammad Mustafa Taye
7. Xinwang Liu
8. Xiaoshi Wu

Citations in the corpus

• Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks (2021, methodology): “To simplify this problem, previous machine learning research has focused on developing specialized models for inputs from certain restricted modality, e.g ., Convolutional Neural Networks [39] for visual recognition and Transformers [69] for natural language processing.”
• A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, methodology): “2) CNN Model: To learn deeper features, convolutional neural networks (CNNs) [64], [65] are integrated with KGR models.”
• A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU (2023, background): “CNNs are feedforward neural networks that leverage convolutional structures to extract features from data [12].”
• Understanding of Machine Learning with Deep Learning: Architectures, Workflow, Applications and Future Directions (2023, methodology): “12 , 91 The application of neural network-based DL technology is widespread across many industries and areas of study, including healthcare, sentiment analysis, NLP, the id of images, BI, cybersecurity, and many more [45,52,53].”
• Convolutional Neural Networks: A Survey (2023, neutral): “Convolutional neural networks (CNNs) [14–16] are a popular type of ML model that have been widely utilized for various tasks, including image recognition [17–20], speech recognition [21–25], and NLP [26–30].”
• Revealing Geography-Driven Signals in Zone-Level Claim Frequency Models: An Empirical Study using Environmental and Visual Predictors (2026, unknown): “Finally, CNNs apply downsampling operations (e.g., pooling) that reduce spatial resolution while retaining useful information (Lecun, Bottou, Bengio, and Haffner, 1998; Li, Liu, Yang, Peng, and Zhou, 2021).”