Deep Learning for Computer Vision: A Brief Review

By Athanasios Voulodimos, N. Doulamis, Anastasios D. Doulamis, Eftychios E. Protopapadakis. 2018

3,350 citations recorded by the source corpus.

Over the last years deep learning methods have been shown to outperform previous state-of-the-art machine learning techniques in several fields, with computer vision being one of the most prominent cases. This review paper provides a brief overview of some of the most significant deep learning schemes used in computer vision problems, that is, Convolutional Neural Networks, Deep Boltzmann Machines and Deep Belief Networks, and Stacked Denoising Autoencoders. A brief account of their history, structure, advantages, and limitations is given, followed by a description of their applications in various computer vision tasks, such as object detection, face recognition, action and activity recognition, and human pose estimation. Finally, a brief overview is given of future directions in designing deep learning schemes for computer vision problems and the challenges involved therein.

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

Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities (2021, background): “ogy [159] could be employed by malicious actors to rapidly identify individuals sharing their pictures online, whether publicly or in direct messages.”
Data-centric Artificial Intelligence: A Survey (2023, neutral): “…witnessed dramatic progress in Artificial Intelligence (AI) across various directions, such as natural language processing [45] and computer vision [224], which has also made a profound impact on nearly every other domain, spanning recommender system [267], healthcare [150], biology [237], finance…”
Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2021, methodology): “Additionally, HAR with image/video processing has been extensively studied in the computer vision community [286, 310], and the methodologies commonly used differ significantly from techniques used for IMUs, EEG, PPG, etc.”
Sensor-based and vision-based human activity recognition: A comprehensive survey (2020, methodology): “Through the backpropagation process, it automatically extracts abstract features from input data [216] .”
Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review (2020, background): “focused on reviewing DL applications in visual data [19, 20]”
A review of deep learning used in the hyperspectral image analysis for agriculture (2021, methodology): “…of deep learning, deep learning models have recently been successfully adopted in various areas such as computer vision (Dan et al. 2011; Athanasios et al. 2018; Voulodimos et al. 2018), speech recognition (Hinton et al. 2012), and other similarly complex data processing (Garcia-Garcia…”
A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trends (2019, background): “Deep Learning for Computer Vision: A Brief Review [229] A Survey on Deep Learning Methods for Robot Vision [230] Deep learning for visual understanding: A review [228] Deep Learning Advances in Computer Vision with 3D Data: A Survey [231] Visualizations of Deep Neural Networks in Computer Vision: A ”
Natural language processing applied to mental illness detection: a narrative review (2022, background): “Advances in deep learning methods have brought breakthroughs in many ﬁ elds including computer vision 113 , NLP 114 , and signal processing 115 .”
State of the Art in Defect Detection Based on Machine Vision (2021, background): “There are three main types of neural layers that play different roles in a CNN: convolutional layers, pooling layers, and fully connected layers [172, 173].”
Stacked Autoencoders Driven by Semi-Supervised Learning for Building Extraction from near Infrared Remote Sensing Imagery (2021, background): “Among the most popular deep models adopted are the Convolutional Neural Networks (CNN) [8,9] which give excellent performance in remote sensing imagery data for classification purposes.”
Object detection using YOLO: challenges, architectural successors, datasets and applications (2022, methodology): “The common deep learning models can be utilized for any computer vision task includes Convolution Neural Network (CNN), Deep Belief Networks (DBN), Deep Boltzmann Machines (DBM), Restricted Boltzmann Machines (RBM), and Stacked Autoencoders [71].”
Deep Learning vs. Traditional Computer Vision (2019, background): “eep Learning workflow. Figure from [8]. The development of CNNs has had a tremendous influence in the field of CV in recent years and is responsible for a big jump in the ability to recognize objects [9]. This burst in progress has been enabled by an increase in computing power, as well as an increa”