A Guide to Convolutional Neural Networks for Computer Vision

By Salman Hameed Khan, Hossein Rahmani, Syed Afaq Ali Shah, Mohammed Bennamoun. 2018

617 citations recorded by the source corpus.

Computer vision has become increasingly important and effective in recent years due to its wide-ranging applications in areas as diverse as smart surveillance and monitoring, health and medicine, sports and recreation, robotics, drones, and self-driving cars. Visual recognition tasks, such as image classification, localization, and detection, are the core building blocks of many of these applications, and recent developments in Convolutional Neural Networks (CNNs) have led to outstanding performance in these state-of-the-art visual recognition tasks and systems. As a result, CNNs now form the crux of deep learning algorithms in computer vision. This self-contained guide will benefit those who seek to both understand the theory behind CNNs and to gain hands-on experience on the application of CNNs in computer vision. It provides a comprehensive introduction to CNNs starting with the essential concepts behind neural networks: training, regularization, and optimization of CNNs. The book also discusses a wide range of loss functions, network layers, and popular CNN architectures, reviews the different techniques for the evaluation of CNNs, and presents some popular CNN tools and libraries that are commonly used in computer vision. Further, this text describes and discusses case studies that are related to the application of CNN in computer vision, including image classification, object detection, semantic segmentation, scene understanding, and image generation. This book is ideal for undergraduate and graduate students, as no prior background knowledge in the field is required to follow the material, as well as new researchers, developers, engineers, and practitioners who are interested in gaining a quick understanding of CNN models.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

An Adaptive Random Path Selection Approach for Incremental Learning. (2019, background): “A typical example is the transfer learning scenario where a model pre-trained on a source task is ﬁne-tuned to a target task, resulting in overriding the previously learned information and consequently degrading the performance on source task [2].”
Random Path Selection for Incremental Learning (2019, background): “As an example, in a typical transfer learning scenario, when a model pre-trained on a source task is adapted to another task by fine-tuning its weights, its performance significantly degrades on the source task whose weights are overridden by the newly learned parameters [13].”
Artificial Intelligence and Marketing: Pitfalls and Opportunities (2020, background): “A convolutional neural network (Khan, Rahmani, & Shah, 2018) is typically a deep-learning, feedforward neural network that contains at least one convolutional layer.”
iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images (2019, background): “…[8], MSCOCO [17], Cityscapes [6] and ADE20K [34] These datasets enabled deep convolutional neural networks (CNN), that are data hungry in nature [14], to show unprecedented performance in scene understanding tasks such as image classiﬁcation [29, 11, 30], object detection [27, 26, 19], semantic…”
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation (2020, methodology): “The advent of deep learning techniques in computer vision [1] coupled with the increasing availability of large training datasets, have led to a third generation of methods that are able to recover the lost dimension.”
On the link between conscious function and general intelligence in humans and machines (2022, background): “, 2017), successfully exploit this property, making them the most popular form of AI model used within computer vision applications (Khan et al., 2018).”
CycleISP: Real Image Restoration via Improved Data Synthesis (2020, background): “Several recent methods use deep CNNs [4, 7, 25, 28, 45, 64, 65, 2] and demonstrate promising denoising performance.”
Striking the Right Balance With Uncertainty (2019, background): “Despite an overwhelming success of deep neural networks on computer vision problems, learning from highly imbalanced sets is still an open problem for deep learning [24].”
A Deep Journey into Super-resolution (2019, methodology): “Alongside SR, deep learning algorithms have shown promising results on other sub-fields in Artificial Intelligence [13] such as object classification [14] and detection [15], natural language processing [16], [17], image processing [18], [19], and audio signal processing [20].”
Artificial intelligence in recommender systems (2020, methodology): “In particular, CNN has been widely adopted for recognition and detection tasks [80], which has resulted in huge changes being made in image processing, not only in academia but also in industry.”