Filters








868 Hits in 2.5 sec

Laplacian Denoising Autoencoder [article]

Jianbo Jiao, Linchao Bao, Yunchao Wei, Shengfeng He, Honghui Shi, Rynson Lau, Thomas S. Huang
2020 arXiv   pre-print
In this paper, we propose to learn data representations with a novel type of denoising autoencoder, where the noisy input data is generated by corrupting latent clean data in the gradient domain.  ...  This can be naturally generalized to span multiple scales with a Laplacian pyramid representation of the input data.  ...  The proposed Laplacian denoising autoencoder performs data reconstruction in the Laplacian pyramid space across multiple scales.  ... 
arXiv:2003.13623v1 fatcat:uel6btlupzbarey7rvr6i6ya7i

Learning with Feature Network and Label Network Simultaneously

Yingming Li, Ming Yang, Zenglin Xu, Zhongfei (Mark) Zhang
2017 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In more details, the proposed algorithm first constructs a feature network and a label network with marginalized linear denoising autoencoder in data feature set and label set, respectively, and then learns  ...  It illustrates that the constructed feature network by marginalized linear denoising autoencoder is more effective than that by graph Laplacian.  ...  In addition, (Vincent et al. 2008 ) trains robust denoising autoencoders with dropout noise.  ... 
doi:10.1609/aaai.v31i1.10715 fatcat:duq2ibcnqfadza3i6qahj5ksh4

Marginalized Denoising Autoencoder via Graph Regularization for Domain Adaptation [chapter]

Yong Peng, Shen Wang, Bao-Liang Lu
2013 Lecture Notes in Computer Science  
To explicitly preserve the intrinsic structure of data, this paper proposes a marginalized Denoising Autoencoders via graph Regularization (GmSDA) in which the autoencoder based framework can learn more  ...  Recently neural network based on Stacked Denoising Auto-Encoders (SDA) and its marginalized version (mSDA) have shown promising results on learning domain-invariant features.  ...  Marginalized Denoising Autoencoders mSDA is a linearized version of SDA, in which the building block of mSDA is a single layer denoising autoencoder.  ... 
doi:10.1007/978-3-642-42042-9_20 fatcat:ijeyc43g2ncsfhstcnj7w23bgm

The Potential Energy of an Autoencoder

Hanna Kamyshanska, Roland Memisevic
2015 IEEE Transactions on Pattern Analysis and Machine Intelligence  
integrating the reconstruction function of the autoencoder.  ...  Recent work has shown how certain autoencoders can be associated with an energy landscape, akin to negative log-probability in a probabilistic model, which measures how well the autoencoder can represent  ...  autoencoder with modulus activation; factored denoising autoencoder with hyperbolic, modulus, squared, and rectifier activation.  ... 
doi:10.1109/tpami.2014.2362140 pmid:26357347 fatcat:5kj7km4eofaijjwqely7duv47y

Fast mesh denoising with data driven normal filtering using deep variational autoencoders

Stavros Nousias, Gerasimos Arvanitis, Aris S. Lalos, Konstantinos Moustakas
2020 Zenodo  
The proposed approach employs conditional variational autoencoders to effectively filter face normals.  ...  In this work, we propose a fast and robust denoising method for dense 3D scanned industrial models.  ...  AUTOENCODER ARCHITECTURES FOR 3D MESH DENOISING This section presents the mesh denoising pipeline.  ... 
doi:10.5281/zenodo.3865275 fatcat:p7dbz6ya2bc5hfgtywielvuipq

Fast mesh denoising with data driven normal filtering using deep variational autoencoders

Stavros Nousias, Gerasimos Arvanitis, Aris Lalos, Konstantinos Moustakas
2020 IEEE Transactions on Industrial Informatics  
The proposed approach employs conditional variational autoencoders to effectively filter face normals.  ...  In this work, we propose a fast and robust denoising method for dense 3D scanned industrial models.  ...  AUTOENCODER ARCHITECTURES FOR 3-D MESH DENOISING This section presents the mesh denoising pipeline.  ... 
doi:10.1109/tii.2020.3000491 fatcat:g2t5nlhegnexnepifvv46nfiee

Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance [article]

Giancarlo Paoletti, Jacopo Cavazza, Cigdem Beyan, Alessio Del Bue
2022 arXiv   pre-print
We propose a new architecture with a convolutional autoencoder that uses graph Laplacian regularization to model the skeletal geometry across the temporal dynamics of actions.  ...  SeBiReNet [18] uses a Siamese denoising autoencoder is used with feature disentanglement, showing good performance across pose denoising and unsupervised cross-view HAR.  ...  Our method is based on convolutional autoencoders (AE) and adapting Laplacian Regularization (L) to capturing the pose geometry in time.  ... 
arXiv:2204.10312v1 fatcat:7oxxnvlmxjhvhnjlzohvk6rsse

Graph Regularized Autoencoder and its Application in Unsupervised Anomaly Detection [article]

Imtiaz Ahmed, Travis Galoppo, Xia Hu, Yu Ding
2021 arXiv   pre-print
Autoencoder is a popular mechanism to accomplish dimensionality reduction.  ...  We use this MST-based distance metric to replace the Euclidean distance metric in the embedding function of autoencoders and develop a new graph regularized autoencoder, which outperforms a wide range  ...  To prevent such risk, a variant of autoencoder is introduced, known as Denoising Autoencoder [37] .  ... 
arXiv:2010.15949v2 fatcat:t4iog763mncpbi5wene3puvpty

Graph Regularized Autoencoder and its Application in Unsupervised Anomaly Detection

Imtiaz Ahmed, Travis Galoppo, Xia Hu, Yu Ding
2021 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Autoencoder is a popular mechanism to accomplish dimensionality reduction.  ...  We use this MST-based distance metric to replace the Euclidean distance metric in the embedding function of autoencoders and develop a new graph regularized autoencoder, which outperforms a wide range  ...  To prevent such risk, a variant of autoencoder is introduced, known as Denoising Autoencoder [36] .  ... 
doi:10.1109/tpami.2021.3066111 pmid:33729925 fatcat:z4zuy43ltbb3nbfrlh3x4a5jxe

Multimodal Data Visualization and Denoising with Integrated Diffusion [article]

Manik Kuchroo, Abhinav Godavarthi, Alexander Tong, Guy Wolf, Smita Krishnaswamy
2022 arXiv   pre-print
We show the utility of this joint operator in data denoising, visualization and clustering, performing better than other methods to integrate and analyze multimodal data.  ...  We also compared to non-diffusion based embeddings produced by cycle GANs, autoencoders and domain transfer autoencoders.  ...  kernel affinity, L u is the unnormalized graph Laplacian.  ... 
arXiv:2102.06757v3 fatcat:awoeg424djhafanb5zmf5wi72y

Stacked Denoising Extreme Learning Machine Autoencoder Based on Graph Embedding for Feature Representation

Hongwei Ge, Weiting Sun, Mingde Zhao, Yao Yao
2019 IEEE Access  
INDEX TERMS Extreme learning machine, stacked autoencoder, denoising, graph embedding.  ...  In this paper, a graph embedding-based denoising extreme learning machine autoencoder (GDELM-AE) is proposed for capturing the structure of the inputs.  ...  STACKED GRAPH EMBEDDED DENOISING ELM (SGD-ELM) In this section, we firstly propose a graph embedding based denoising extreme learning machine autoencoder (GDELM-AE) for representing the inputs.  ... 
doi:10.1109/access.2019.2894014 fatcat:sl6lqubnwfh3naklm6hkpdsihm

Generative Adversarial Networks for Robust Cryo-EM Image Denoising [article]

Hanlin Gu, Yin Xian, Ilona Christy Unarta, Yuan Yao
2022 arXiv   pre-print
In this paper, we approach the robust image denoising problem in Cryo-EM by a joint Autoencoder and Generative Adversarial Networks (GAN) method.  ...  Equipped with robust ℓ_1 Autoencoder and some designs of robust β-GANs, one can stabilize the training of GANs and achieve the state-of-the-art performance of robust denoising with low SNR data and against  ...  The Autoencoder is good at data denoising and dimension reduction.  ... 
arXiv:2008.07307v4 fatcat:6ee22w65zjhgpevxnthy3f6clm

Distributed Evolution of Deep Autoencoders [article]

Jeff Hajewski, Suely Oliveira, Xiaoyu Xing
2020 arXiv   pre-print
We demonstrate the effectiveness of this system on the tasks of manifold learning and image denoising.  ...  impact the overall performance of the autoencoder.  ...  Some of the more popular techniques are Isomap [24] , locally-linear embeddings [25] , and Laplacian eigenmaps [26] . Autoencoders are another technique for manifold learning.  ... 
arXiv:2004.07607v1 fatcat:3trruywqebeplmemcqnnrf3vaa

Dynamic MRI using deep manifold self-learning [article]

Abdul Haseeb Ahmed, Hemant Aggarwal, Prashant Nagpal, Mathews Jacob
2019 arXiv   pre-print
Our method learns the manifold structure in the dynamic data from navigators using autoencoder network. The trained autoencoder is then used as a prior in the image reconstruction framework.  ...  Autoencoder Input Autoencoder Output EXPERIMENTS & RESULTS We first test the denoising ability of our proposed scheme on the data recovered by SToRM method in Fig 2.  ...  We have trained the denoising autoencoder using navigator data, to learn the dynamic structure in the cardiac CINE images.  ... 
arXiv:1911.02492v1 fatcat:x723kopumzaxzotiojxsif3ps4

Diffusion Nets [article]

Gal Mishne, Uri Shaham, Alexander Cloninger, Israel Cohen
2015 arXiv   pre-print
Stacking the encoder and decoder together constructs an autoencoder, which we term a diffusion net, that performs out-of-sample-extension as well as outlier detection.  ...  We pre-train every hidden layer as a denoising autoencoder [21] with a sparsity term.  ...  The autoencoder can be used for both outlier detection and denoising. Our framework is presented in Algorithms 1, 2 and 3.  ... 
arXiv:1506.07840v1 fatcat:lugeo4k4fzgp3edmxvbvcy7tuu
« Previous Showing results 1 — 15 out of 868 results