Image annotation using deep learning: A review

Abstract

In the last few years, deep learning has led to huge success in the field of computer vision and natural language understanding and also in the interplay between them. Among different types of deep learning models, convolutional neural networks have been most extensively studied for the tasks related to visual perception and machine vision. Due to lack of computational resources and training data, it is very hard to the use high-capacity convolutional neural network without overfitting. But recent growth in the availability of annotated data and high performance GPUs have made it possible to obtain state-of-the-art results using convolutional neural networks. In this paper, we present a review on how and why CNNs are extensively getting used in the computer vision community. It also introduces an application of ConvNets for annotating contents of the image by partially localizing them.