Deep Learning For Computer Vision

Abstract

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 quick overview of a number of the foremost significant deep learning schemes utilized 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 an outline of their applications in various computer vision tasks, like object detection, face recognition, action and activity recognition, and human pose estimation. Finally, a quick overview is given of future directions in designing deep learning schemes for computer vision problems and therefore the challenges involved therein.