Filters








5,298 Hits in 17.0 sec

Semi-Supervised Dimensionality Reduction of Hyperspectral Image Based on Sparse Multi-Manifold Learning

Hong Huang, Fulin Luo, Zezhong Ma, Hailiang Feng
<span title="">2015</span> <i title="Scientific Research Publishing, Inc,"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3knnadznr5bfriv5arevcxfm7m" style="color: black;">Journal of Computer and Communications</a> </i> &nbsp;
In this paper, we proposed a new semi-supervised multi-manifold learning method, called semisupervised sparse multi-manifold embedding (S 3 MME), for dimensionality reduction of hyperspectral image data  ...  S 3 MME exploits both the labeled and unlabeled data to adaptively find neighbors of each sample from the same manifold by using an optimization program based on sparse representation, and naturally gives  ...  Funds for the Central Universities of China (106112013CDJZR125501, 1061120131204), and Chongqing University Postgraduates' Innovation Project (CYB15052).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.4236/jcc.2015.311006">doi:10.4236/jcc.2015.311006</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5b2ibfvilzejnav4rrveulspau">fatcat:5b2ibfvilzejnav4rrveulspau</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170923065830/http://file.scirp.org/pdf/JCC_2015111916231183.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/92/8f/928f836b5f7c05790031d372f4d725b4069d0318.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.4236/jcc.2015.311006"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Visual Understanding via Multi-Feature Shared Learning With Global Consistency

Lei Zhang, David Zhang
<span title="">2016</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/sbzicoknnzc3tjljn7ifvwpooi" style="color: black;">IEEE transactions on multimedia</a> </i> &nbsp;
is much improved through the semi-supervised learning with global label consistency.  ...  This paper studies visual understanding via a newly proposed l_2-norm based multi-feature shared learning framework, which can simultaneously learn a global label matrix and multiple sub-classifiers with  ...  For better exploiting the manifold structure of each feature in semi-supervised learning, motivated by the spirit of joint learning concepts discussed above, we target at proposing a multi-feature shared  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tmm.2015.2510509">doi:10.1109/tmm.2015.2510509</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cp4rtxaha5dblgrg6sugmsa7sa">fatcat:cp4rtxaha5dblgrg6sugmsa7sa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190728165346/http://www.leizhang.tk:80/resources/TMM-2015.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4c/56/4c5644a366516bef25645676e6112f6aa17b8fe1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tmm.2015.2510509"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Novel Adaptive Multi-view Non-Negative Graph Semi-supervised ELM

Feng Zheng, Zeyu Liu, Yijian Chen, Jiacheng An, Yanyan Zhang
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
This paper represents a semi-supervised learning framework, which integrates multi-view learning, extreme learning machine (ELM) and graph-based semi-supervised learning.  ...  Unlike traditional graph-based semi-supervised learning methods, which only can label propagation and build linear regression models for single or multi-view data, our proposed method has an obvious advantage  ...  sparse graph framework (NNSG), (d) a multi-view semi-supervised learning [20] , (e) Semi-supervised ELM(SS-ELM), and (f) Adaptive multiple graph regularized semi-supervised ELM(AMGE-ELM).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2998428">doi:10.1109/access.2020.2998428</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5kuens7aibb35kgjkdyxovx76q">fatcat:5kuens7aibb35kgjkdyxovx76q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210427063731/https://ieeexplore.ieee.org/ielx7/6287639/8948470/09103516.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/76/e7/76e7110b62839f3573e060a952f7fb1c11481392.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2998428"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Semi-supervised Multi-view Manifold Discriminant Intact Space Lear

<span title="2018-09-30">2018</span> <i title="Korean Society for Internet Information (KSII)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hupfbobgkvepdnt5g32qxkypsy" style="color: black;">KSII Transactions on Internet and Information Systems</a> </i> &nbsp;
Semi-supervised multi-view latent space learning is gaining considerable popularity recently in many machine learning applications due to the high cost and difficulty to obtain the large amount of label  ...  Although some semi-supervised multi-view latent space learning methods have been presented, there is still much space for improvement: 1) How to learn latent discriminant intact feature representations  ...  Adaptive Multi-view Semi-supervised Nonnegative Matrix Factorization Adaptive multi-view semi-supervised nonnegative matrix factorization (AMVNMF) [28] is developed for accurate clustering multi-view  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3837/tiis.2018.09.011">doi:10.3837/tiis.2018.09.011</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/v5ghd5iuavegtmlawnvnous3si">fatcat:v5ghd5iuavegtmlawnvnous3si</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200506193158/http://www.itiis.org/digital-library/manuscript/file/21869/TIISVol12No9-11.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/67/62/6762274968d6abceceaa7fa4803eda0131372e1e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3837/tiis.2018.09.011"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

An Adaptive Semisupervised Feature Analysis for Video Semantic Recognition

Minnan Luo, Xiaojun Chang, Liqiang Nie, Yi Yang, Alexander G. Hauptmann, Qinghua Zheng
<span title="">2018</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/snhjqrgxbff5teva5lfasxmfr4" style="color: black;">IEEE Transactions on Cybernetics</a> </i> &nbsp;
Video semantic recognition usually suffers from the curse of dimensionality and the absence of enough high-quality labeled instances, thus semi-supervised feature selection gains increasing attentions  ...  Most of the previous methods assume that videos with close distance (neighbors) have similar labels and characterize the intrinsic local structure through a predetermined graph of both labeled and unlabeled  ...  -Structural Feature Selection with Sparsity [25] [SFSS]: This semi-supervised feature selection algorithms incorporates joint feature selection and semi-supervised learning into a single framework.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tcyb.2017.2647904">doi:10.1109/tcyb.2017.2647904</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/28237940">pmid:28237940</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/luc3o3xlcbav3e47upkev3ituy">fatcat:luc3o3xlcbav3e47upkev3ituy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170315225625/http://www.cs.cmu.edu:80/~uqxchan1/papers/CYB17_OGE_SFS.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/31/e6/31e68bd643e264d7971fc99ba6c344842bbf9641.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tcyb.2017.2647904"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Structure-induced Framework for Multi-Label Feature Selection with Highly Incomplete Labels

Tiantian Xu, Long Zhao
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
INDEX TERMS Feature selection, multi-label learning, weakly-supervised learning, label correlation.  ...  Feature selection is guided by the label structure reconstruction, and highly incomplete labels are recovered via the structure transferred from feature space.  ...  [6] : a recently proposed semi-supervised multilabel learning approach combining manifold learning with shared subspace construction to select discriminative features. • SCFS [7] : a latest semi-supervised  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2987922">doi:10.1109/access.2020.2987922</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/n3irfpsjfbf3thgisadso4vxle">fatcat:n3irfpsjfbf3thgisadso4vxle</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210718033712/https://ieeexplore.ieee.org/ielx7/6287639/8948470/09066973.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/34/1f/341f44f79b331c3b11acfe60148987018cdb9b1d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2987922"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Improving head and body pose estimation through semi-supervised manifold alignment

Alexandre Heili, Jagannadan Varadarajan, Bernard Ghanem, Narendra Ahuja, Jean-Marc Odobez
<span title="">2014</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/anlh4tvwprcrtoxv5d4h6a7rye" style="color: black;">2014 IEEE International Conference on Image Processing (ICIP)</a> </i> &nbsp;
Index Termshead and body pose, weak labels, manifold, semi-supervised, domain adaptation, surveillance.  ...  While this previous approach showed promising results, the learning of the underlying manifold structure of the features in the train and target data and the need to align them were not explored despite  ...  The labels of the training set and the (weak) labels within the adaptation set are used to bias and align manifolds.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icip.2014.7025383">doi:10.1109/icip.2014.7025383</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icip/HeiliVGAO14.html">dblp:conf/icip/HeiliVGAO14</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xlopdvyy6fcrxegny44euajdie">fatcat:xlopdvyy6fcrxegny44euajdie</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170818181218/https://infoscience.epfl.ch/record/200303/files/Heili_ICIP_2014.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a8/81/a8814144b96982e447117b8983dd33c6ca3c3024.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icip.2014.7025383"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Domain Adaptation for Visual Applications: A Comprehensive Survey [article]

Gabriela Csurka
<span title="2017-03-30">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The aim of this paper is to give an overview of domain adaptation and transfer learning with a specific view on visual applications.  ...  Finally, we conclude the paper with a section where we relate domain adaptation to other machine learning solutions.  ...  The Semi-supervised Domain Adaptation with Subspace Learning [118] jointly explores invariant lowdimensional structures across domains to correct data distribution mismatch and leverages available unlabeled  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1702.05374v2">arXiv:1702.05374v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5va4oz4evjfhxgxddflpbb6pxi">fatcat:5va4oz4evjfhxgxddflpbb6pxi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200907090703/https://arxiv.org/pdf/1702.05374v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/33/0d/330dda431e0343a96f9d630a0b4ee526bd93ad11.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1702.05374v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Survey on Concept Factorization: From Shallow to Deep Representation Learning [article]

Zhao Zhang, Yan Zhang, Mingliang Xu, Li Zhang, Yi Yang, Shuicheng Yan
<span title="2021-01-31">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The quality of learned features by representation learning determines the performance of learning algorithms and the related application tasks (such as high-dimensional data clustering).  ...  of CF and find the most appropriate CF techniques to deal with particular applications.  ...  ACKNOWLEDGMENT This work is partially supported by the National Natural Science Foundation of China (61672365) and the Fundamental Research Funds for the Central Universities of China (JZ2019H-  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.15840v3">arXiv:2007.15840v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ahun2mogmfapxe4mqhqlsakyku">fatcat:ahun2mogmfapxe4mqhqlsakyku</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826010207/https://arxiv.org/ftp/arxiv/papers/2007/2007.15840.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/dc/23/dc23af2dde52c6a72f28fa9f0b8c77afaff9446f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.15840v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Semi-Supervised Ground-to-Aerial Adaptation with Heterogeneous Features Learning for Scene Classification

Zhipeng Deng, Hao Sun, Shilin Zhou
<span title="2018-05-10">2018</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/fw2uac7a5jggbfgqwh2wqy7yxu" style="color: black;">ISPRS International Journal of Geo-Information</a> </i> &nbsp;
To make use of unlabeled target samples, a manifold regularized semi-supervised learning process is incorporated into our framework.  ...  Specifically, a semi-supervised manifold-regularized multiple-kernel-learning (SMRMKL) algorithm is proposed for solving these problems.  ...  The authors would also like to thank the anonymous reviewers for their very competent comments and helpful suggestions. Conflicts of Interest: The authors declare no conflict of interest.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/ijgi7050182">doi:10.3390/ijgi7050182</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/it6tok2fpjgmddwtfcrvaxz3dq">fatcat:it6tok2fpjgmddwtfcrvaxz3dq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190504201144/https://res.mdpi.com/ijgi/ijgi-07-00182/article_deploy/ijgi-07-00182-v2.pdf?filename=&amp;attachment=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/db/b2/dbb202b5dc073a2284044b4903a6057ac54c034f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/ijgi7050182"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Semi-Supervised Multiple Feature Analysis for Action Recognition

Sen Wang, Zhigang Ma, Yi Yang, Xue Li, Chaoyi Pang, Alexander G. Hauptmann
<span title="">2014</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/sbzicoknnzc3tjljn7ifvwpooi" style="color: black;">IEEE transactions on multimedia</a> </i> &nbsp;
The main paradigm of graph-based semi-supervised learning is to utilize relations between labeled and unlabeled data by exploring the manifold structure.  ...  To deal with this problem, a graph is utilized to approximate the density and manifold information for semi-supervised learning in the framework.  ...  He mainly focuses his research on machine learning and relevant applications in computer vision and data mining, e.g., human action recognition, social network event detection, etc. Zhigang  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tmm.2013.2293060">doi:10.1109/tmm.2013.2293060</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/caiu5if4trf73fmpqs5jdbjudi">fatcat:caiu5if4trf73fmpqs5jdbjudi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321155827/https://apps.dtic.mil/dtic/tr/fulltext/u2/1024300.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a4/05/a40557090165ca9374927e03b0f179cf43256df0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tmm.2013.2293060"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Machine learning and intelligence science: Sino-foreign interchange workshop IScIDE2010 (A)

Lei Xu, Yanda Li
<span title="">2011</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/qviyf4uvojarvlkosv77blu3qa" style="color: black;">Frontiers of Electrical and Electronic Engineering in China</a> </i> &nbsp;
Regarding labels as inputs and data points as outputs while class structures as a system, we can observe that semi-blind deconvolution and semi-supervised learning share a similar concept but differ in  ...  semi-supervised learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11460-011-0136-0">doi:10.1007/s11460-011-0136-0</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tsrdewj6s5brtnkfo4omuyuu2u">fatcat:tsrdewj6s5brtnkfo4omuyuu2u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190501193223/https://link.springer.com/content/pdf/10.1007%2Fs11460-011-0136-0.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e2/85/e28598839f752e862e687e5a32e7fa00a344769f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11460-011-0136-0"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Ensemble Manifold Segmentation for Model Distillation and Semi-supervised Learning [article]

Dengxin Dai, Wen Li, Till Kroeger, Luc Van Gool
<span title="2018-04-06">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our experiments show that the manifold structures are effectively utilized for both unsupervised and semi-supervised learning.  ...  CNNs are trained on these ensembles under a multi-task learning framework to conform to the manifold. ManifoldNet can be trained with only the pseudo labels or together with task-specific labels.  ...  Experiments show that it effectively utilizes manifold structures for both unsupervised and semi-supervised learning. Related Work Manifold Learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.02201v1">arXiv:1804.02201v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pdcy5tyoorf23kmnsa6blpmgty">fatcat:pdcy5tyoorf23kmnsa6blpmgty</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200923091351/https://arxiv.org/pdf/1804.02201v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e1/68/e168febd2bfd920584a1d5f8530040ee85c874f5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.02201v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Scene Recognition via Semi-Supervised Multi-Feature Regression

Caixia Zheng, Jianyu Chen, Jun Kong, Yugen Yi, Yinghua Lu, Jianzhong Wang, Chong Liu
<span title="">2019</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
Hence, to effectively fuse the multiple features of each image and employ the information of both labeled and unlabeled images for scene recognition, we proposed a semi-supervised multi-feature regression  ...  First, the model propagates the labels of labeled data to unlabeled data by utilizing graph-based semi-supervised learning techniques so that both the information regarding unlabeled data and labeled data  ...  with Adaptive Distance Penalty (LRRADP) [70] , Multi-Modal Semi-Supervised Learning Model (MMSSL) [6] , Structural Feature Selection with Sparsity (SFSS) [71] , Multi-view Learning with Adaptive Neighbours  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2019.2935420">doi:10.1109/access.2019.2935420</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/icndllqf6jf2zch5mocejnoova">fatcat:icndllqf6jf2zch5mocejnoova</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210427085054/https://ieeexplore.ieee.org/ielx7/6287639/8600701/08798735.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/19/aa/19aa24a9ec0c33357ff38cfb2018c0d4dfb2575d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2019.2935420"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Multi-GCN: Graph Convolutional Networks for Multi-View Networks, with Applications to Global Poverty [article]

Muhammad Raza Khan, Joshua E. Blumenstock
<span title="2019-01-31">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We show that this method outperforms state-of-the-art semi-supervised learning algorithms on three different prediction tasks using mobile phone datasets from three different developing countries.  ...  labelling in citation networks.  ...  Graph-based semi-supervised learning (GSSL) is a popular approach for semi-supervised learning that treats labeled and unlabeled instances as graph vertices, and relationships between instances as edges  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.11213v1">arXiv:1901.11213v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/eu75x365sjbnrhov3znbovaqdq">fatcat:eu75x365sjbnrhov3znbovaqdq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826080645/https://arxiv.org/pdf/1901.11213v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/db/b4/dbb4035111c12f4bce971bd4c8086e9d62c9eb97.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.11213v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 5,298 results