Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review

By Waseem Rawat, Zenghui Wang. Neural Computation, 2017

3,214 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c1f05b723e53ac4eb1133249b445c0011d42ca79

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

In Computer Vision and Pattern Recognition

Citations in the corpus

DCNN-Based Multi-Signal Induction Motor Fault Diagnosis (2020, background): “In the convolutional layer, a small region of the input is connected to one neuron by a set of trainable weights [35], [47], and different regions are connected to different neurons.”
Deep convolutional neural networks for eigenvalue problems in mechanics (2018, background): “Under the substitution, the harmonic elastodynamic problem in Equation (1) can be formally written as (neglecting the body force)”
A survey of the recent architectures of deep convolutional neural networks (2019, neutral): “xtraction stages and globally analyses the output of all the preceding layers [61]. Consequently, it makes a non-linear combination of selected features, which are used for the classification of data [62]. Accepted in Artificial Intelligence Review (Springer Nature), DOI: 10.1007/s10462-020-09825-6 ”
Deep learning and medical image processing for coronavirus (COVID-19) pandemic: A survey (2020, positive): “One of the predominantly used techniques of NN for image processing is CNN (Gadekallu, Rajput, et al., 2020; Huynh-The, Hua, Pham, & Kim, 2020; Rawat & Wang, 2017).”
Graph convolutional networks for computational drug development and discovery (2019, background): “Deep learning [1] has achieved remarkable success and been widely adopted over the past decade for learning tasks in domains such as natural language processing [2] and computer vision [3].”
Recent advances in deep learning based dialogue systems: a systematic survey (2021, background): “For more detailed mechanism illustrations and other variants of CNNs, readers can refer to these representative algorithm papers or surveys: (Krizhevsky et al., 2012; Zeiler and Fergus, 2014; Simonyan and Zisserman, 2014; Szegedy et al., 2015; He et al., 2016; Aloysius and Geetha, 2017; Rawat and Wa”
Tree-CNN: A Deep Convolutional Neural Network for Lifelong Learning (2018, background): “D EEP Convolutional Neural Networks (DCNNs) have emerged as the leading architecture for large scale image classification in recent years [1].”
A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trends (2019, background): “In [226] the authors introduced MetaQNN, a RL based meta-modeling algorithm to automatically generate CNN architectures for image classiﬁcation by using Q-learning [227] Asurvey on the state-of-the-art machine learning models in the context of NLP [263] Inﬂectional Review of Deep Learning on Natural”
Tree-CNN: A hierarchical Deep Convolutional Neural Network for incremental learning (2018, background): “In recent years Deep Convolutional Neural Networks (DCNNs) have emerged as the leading architecture for large scale image classification [19].”
Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future (2020, methodology): “The CNN as we know it today comes from the field of computer vision, yet the inspiration from the work of Hubel and Wiesel is clearly visible in it (Figure 1; Rawat & Wang, 2017).”
Applications of deep learning in stock market prediction: recent progress (2020, background): “…network family, deep learning has achieved a tremendous success in the past few years, for many different applications including image classification (Rawat & Wang, 2017; Jiang & Zhang, 2020), object detection (Zhao et al., 2019), time series prediction (Brownlee, 2018; Jiang & Zhang, 2018), etc.”