From Auto-encoders to Capsule Networks: A Survey

Abstract

Convolutional Neural Networks are a very powerful Deep Learning structure used in image processing, object classification and segmentation. They are very robust in extracting features from data and largely used in several domains. Nonetheless, they require a large number of training datasets and relations between features get lost in the Max-pooling step, which can lead to a wrong classification. Capsule Networks(CapsNets) were introduced to overcome these limitations by extracting features and their pose using capsules instead of neurons. This technique shows an impressive performance in one-dimensional, two-dimensional and three-dimensional datasets as well as in sparse datasets. In this paper, we present an initial understanding of CapsNets, their concept, structure and learning algorithm. We introduce the progress made by CapsNets from their introduction in 2011 until 2020. We compare different CapsNets series architectures to demonstrate strengths and challenges. Finally, we quote different implementations of Capsule Networks and show their robustness in a variety of domains. This survey provides the state-of-theartof Capsule Networks and allows other researchers to get a clear view of this new field. Besides, we discuss the open issues and the promising directions of future research, which may lead to a new generation of CapsNets.

VIOLA jones algorithm with capsule graph network for deepfake detection

“…Some metrics such as accuracy calculation and error detection rate are probably used. To evaluate the proposed outcome and performance, comparative study on the existing models such as, To evaluate the proposed outcome and performance, the comparative study on existing models such as the VGG-19 ( Simonyan & Zisserman, 2014 ), VIOLA-Jones ( Huang, Shang & Chen, 2019 ), Capsule Net ( El Alaoui-Elfels & Gadi, 2021 ), VIOLA-Jones +Capsule network is analyzed. Evaluation metrics measure the performance using accuracy, specificity, sensitivity, root mean square error (RMSE), mean absolute error (MAE), signal noise ratio (SNR), and peak signal noise ratio (PSNR).…”

Detecting Fake Faces with AI: A Deep Neural Network Improvement Project

“…In conclusion, the findings of a comparison between the detection accuracy of this paper and that of other methods demonstrate that the detection accuracy of this paper is superior. Alaoui, Eifels O, et al [9], demonstrates how to use a convolutional neural network, which is one of the primary networks used to recognise facial features and prevent making mistakes in the identification process. Other networks, ranging from auto-encoders to capsule networks, are also used for this purpose.…”

AlexCapsNet: an integrated architecture for image classification with noise and many categories

“…CapsNet performance is relatively poor in Fashion-MNIST [8] and CIFAR10 [9]. There were two reasons were reported to cause this disparity [10,11,12,6,13]: 1) CapsNet has only two feature extraction layers, leading to the inability to extract semantic information for dynamic routing algorithm; 2) The reconstruction module is ineffective for complicated datasets with noisy backgrounds.…”