Filters








2,842 Hits in 2.5 sec

Deep Belief Networks for Image Denoising [article]

Mohammad Ali Keyvanrad, Mohammad Pezeshki, Mohammad Ali Homayounpour
2014 arXiv   pre-print
Deep Belief Networks which are hierarchical generative models are effective tools for feature representation and extraction.  ...  In this paper, we propose a novel method for image denoising which relies on the DBNs' ability in feature representation. This work is based upon learning of the noise behavior.  ...  Deep Belief Networks One of the main problems in training deep networks is how to initialize weights. It is difficult to optimize the weights in nonlinear Deep Networks with multiple hidden layers.  ... 
arXiv:1312.6158v2 fatcat:736mol5twjdrloa3gc23lvzy2i

Facial Expression Recognition Method Based on Stacked Denoising Autoencoders and Feature Reduction

Jun Zhao, Yan Zhao, Yong Yang, Yong Huang, Inkyu Park
2017 DEStech Transactions on Engineering and Technology Research  
Based on the deep learning theory, a novel facial expression recognition method, which utilizes both Principal Component Analysis (PCA) and stacked denoising autoencoders (SDAE), is proposed in this paper  ...  accuracy than traditional non-deep learning based expression recognition methods.  ...  In the same year, Liu P, et al. proposed the combination of deep belief networks and AdaBoost method for facial expression recognition [10] .  ... 
doi:10.12783/dtetr/iceta2016/6996 fatcat:izifhy6s35cwvm3r7cbb6bvhp4

Deep Learning for Image Denoising: A Survey [article]

Chunwei Tian, Yong Xu, Lunke Fei, Ke Yan
2018 arXiv   pre-print
Morever, we systematically analyze the conventional machine learning methods for image denoising. Finally, we point out some research directions for the deep learning technologies in image denoising.  ...  In this paper, we have an aim to completely review and summarize the deep learning technologies for image denoising proposed in recent years.  ...  Universal denoising networks [22] for image denoising and deep CNN denoiser prior to eliminate multicative noise [34] are also effective for image denoising.  ... 
arXiv:1810.05052v1 fatcat:wmfrfbta4jajrmdj54hwbeejue

Predicting distributions with Linearizing Belief Networks [article]

Yann N. Dauphin, David Grangier
2016 arXiv   pre-print
Such networks are particularly relevant to inverse problems such as image prediction for denoising, or text to speech.  ...  Conditional belief networks introduce stochastic binary variables in neural networks.  ...  ACKNOWLEDGEMENTS The authors would like to thank Marc'Aurelio Ranzato for insightful comments and discussions.  ... 
arXiv:1511.05622v4 fatcat:ta22g5y34zdf5f56ov622ymkoa

Medical Image Denoising Using Convolutional Denoising Autoencoders

Lovedeep Gondara
2016 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW)  
Heterogeneous images can be combined to boost sample size for increased denoising performance.  ...  In this paper we show that using small sample size, denoising autoencoders constructed using convolutional layers can be used for efficient denoising of medical images.  ...  Which is in contrary to the belief that very large training datasets are needed for training deep architectures for good performance.  ... 
doi:10.1109/icdmw.2016.0041 dblp:conf/icdm/Gondara16 fatcat:wcrnxjc2m5elbopqjhxbmaqycm

Deep Learning for Computer Vision: A Brief Review

Athanasios Voulodimos, Nikolaos Doulamis, Anastasios Doulamis, Eftychios Protopapadakis
2018 Computational Intelligence and Neuroscience  
Belief Networks, and Stacked Denoising Autoencoders.  ...  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  ...  Deep Belief Networks and Deep Boltzmann Machines.  ... 
doi:10.1155/2018/7068349 pmid:29487619 pmcid:PMC5816885 fatcat:yeawpj32onfutegmkqpx4p6tsa

Two-Stage Approach to Image Classification by Deep Neural Networks

Gennady Ososkov, Pavel Goncharov, Gh. Adam, J. Buša, M. Hnatič, D. Podgainy
2018 EPJ Web of Conferences  
It is also shown that the deep autoencoders develop the remarkable ability for denoising images after being specially trained.  ...  The paper demonstrates the advantages of the deep learning networks over the ordinary neural networks on their comparative applications to image classifying.  ...  Deep and shallow Neural Networks Deep belief network.  ... 
doi:10.1051/epjconf/201817301009 fatcat:esfxfjstmnac5jrv7m3hrcbw24

Deep Learning in Character Recognition Considering Pattern Invariance Constraints

Oyebade K. Oyedotun, Ebenezer O. Olaniyi, Adnan Khashman
2015 International Journal of Intelligent Systems and Applications  
This research work reviews some of the most successful pre-training approaches to initializing deep networks such as stacked auto encoders, and deep belief networks based on achieved error rates.  ...  Character recognition is a field of machine learning that has been under research for several decades.  ...  the deep belief network.  ... 
doi:10.5815/ijisa.2015.07.01 fatcat:bwbts744lvfajjs7mptyvefyte

Learning structure in gene expression data using deep architectures, with an application to gene clustering [article]

Aman Gupta, Haohan Wang, Madhavi Ganapathiraju
2015 bioRxiv   pre-print
We propose that our deep architectures can be treated as empirical versions of Deep Belief Networks (DBNs).  ...  In this paper, we use deep architectures pre-trained in an unsupervised manner using denoising autoencoders as a preprocessing step for a popular unsupervised learning task.  ...  ACKNOWLEDGMENT AG is grateful to Volkan Cirik for valuable discussions on the capabilities of autoencoders.  ... 
doi:10.1101/031906 fatcat:4p6xmcqrbfec3h5g62klr3zkwu

Learning structure in gene expression data using deep architectures, with an application to gene clustering

Aman Gupta, Haohan Wang, Madhavi Ganapathiraju
2015 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)  
We propose that our deep architectures can be treated as empirical versions of Deep Belief Networks (DBNs).  ...  In this paper, we use deep architectures pre-trained in an unsupervised manner using denoising autoencoders as a preprocessing step for a popular unsupervised learning task.  ...  ACKNOWLEDGMENT AG is grateful to Volkan Cirik for valuable discussions on the capabilities of autoencoders.  ... 
doi:10.1109/bibm.2015.7359871 dblp:conf/bibm/GuptaWG15 fatcat:erhxclgfdng3hgy6pq4ootzb7m

Deep Learning on Image Denoising: An overview [article]

Chunwei Tian, Lunke Fei, Wenxian Zheng, Yong Xu, Wangmeng Zuo, Chia-Wen Lin
2020 arXiv   pre-print
We first classify the deep convolutional neural networks (CNNs) for additive white noisy images; the deep CNNs for real noisy images; the deep CNNs for blind denoising and the deep CNNs for hybrid noisy  ...  However, there has thus far been little related research to summarize the different deep learning techniques for image denoising.  ...  Stacked auto-encoders (SARs) [80] and deep belief networks (DBNs) [17, 79] are typical deep neural networks.  ... 
arXiv:1912.13171v4 fatcat:4ts2xpivhreptelbgeqhljjiri

Deep Learning Techniques for Face Recognition: A Review

Neenu Daniel
2019 International Journal for Research in Applied Science and Engineering Technology  
Deep learning techniques are becoming popular as it is able to handle large datasets. This paper provides an overview of deep learning techniques and its usage for face recognition.  ...  It is a technology capable of identifying and verifying an individual from images and videos.  ...  Deep Belief Networks Deep Belief Networks are one of the successful models of Deep learning. It consists of many layers of hidden units with a unsupervised learning algorithm.  ... 
doi:10.22214/ijraset.2019.6271 fatcat:ng6adarrwvbenlsphuffeovyzm

Multiscale residual fusion network for image denoising

Cheng Yao, Yibin Tang, Jia Sun, Yuan Gao, Changping Zhu
2021 IET Image Processing  
Deep-learning methods have been developed in recent years and have achieved dramatic improvements for image denoising.  ...  Experiments demonstrated that the MRF-Net outperformed several state-of-the-art model-based and deep-learning methods in both blind and non-blind image denoising tests.  ...  A convolutional dictionary learning was employed for denoising by using some deep-learning-based image priors [13] .  ... 
doi:10.1049/ipr2.12394 fatcat:uly3js4tgbh7bascqtou4gfbdy

Deep networks for robust visual recognition

Yichuan Tang, Chris Eliasmith
2010 International Conference on Machine Learning  
Deep Belief Networks (DBNs) are hierarchical generative models which have been used successfully to model high dimensional visual data.  ...  Recognition results after denoising are significantly better over the standard DBN implementations for various sources of noise.  ...  Acknowledgements We thank the anonymous reviewers for making this a much better manuscript. This research was supported by NSERC.  ... 
dblp:conf/icml/TangE10 fatcat:xxncjb4amndi7pnwpdy4z6j4ra

A C++ library for Multimodal Deep Learning [article]

Jian Jin
2016 arXiv   pre-print
MDL, Multimodal Deep Learning Library, is a deep learning framework that supports multiple models, and this document explains its philosophy and functionality.  ...  For the last layer, compute δ Figure 5 . 1 : 51 Deep Belief Network A Deep Belief Network (DBN) is a hybrid of a Restricted Boltzmann Machine and a Sigmoid Belief Network.  ...  Training of the Deep Belief Network In training, the Deep Belief Network should maximize the likelihood of the training data.  ... 
arXiv:1512.06927v4 fatcat:2j2pt5x2wzgwpph7osd3xlyzha
« Previous Showing results 1 — 15 out of 2,842 results