Filters








7,067 Hits in 6.0 sec

Semi-supervised Learning with Graphs: Covariance Based Superpixels For Hyperspectral Image Classification [article]

Philip Sellars and Angelica Aviles-Rivero and Nicolas Papadakis and David Coomes and Anita Faul and Carola-Bibane Schönlieb
2019 arXiv   pre-print
In this paper, we present a graph-based semi-supervised framework for hyperspectral image classification.  ...  We then construct a superpixel graph, based on carefully considered feature vectors, before performing classification.  ...  The graph G and the labelling matrix Y are then fed into the Learning with Local and Global Consistency algorithm (LGC) by Zhou et al [13] .  ... 
arXiv:1901.04240v4 fatcat:ddwlkdsuyvdsjg4wvgjy7fsf54

A review of various semi-supervised learning models with a deep learning and memory approach

Jamshid Bagherzadeh, Hasan Asil
2018 Iran Journal of Computer Science  
In semi-supervised learning, labeled data can contribute significantly to accurate pattern extraction. Thus, they can result in better convergence by having greater effects on models.  ...  Based on data types, four learning methods have been presented to extract patterns from data: supervised, semi-supervised, unsupervised, and reinforcement.  ...  Graph-based methods Graph-based semi-supervised learning methods are based on the string theory.  ... 
doi:10.1007/s42044-018-00027-6 fatcat:nccifurxyzc33fa5xfprrlupxq

Semi-Supervised Learning with Graphs: Covariance Based Superpixels For Hyperspectral Image Classification

Philip Sellars, Angelica I. Aviles-Rivero, Nicolas Papadakis, David Coomes, Anita Faul, Carola-Bibiane Schonlieb
2019 IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium  
In this paper, we present a graph-based semi-supervised framework for hyperspectral image classification.  ...  We then construct a superpixel graph, based on carefully considered feature vectors, before performing classification.  ...  The graph G and the labelling matrix Y are then fed into the Learning with Local and Global Consistency algorithm (LGC) by Zhou et al [13] .  ... 
doi:10.1109/igarss.2019.8898189 dblp:conf/igarss/SellarsAPCFS19 fatcat:rwwmcbyhkjc3bndn2lpugpxrzq

Collaborative Graph Convolutional Networks: Unsupervised Learning Meets Semi-Supervised Learning

Binyuan Hui, Pengfei Zhu, Qinghua Hu
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
If the pseudo-label of an unlabeled sample assigned by GMM-VGAE is consistent with the prediction of the semi-supervised GCN, it is selected to further boost the performance of semi-supervised learning  ...  Inspired by the success of unsupervised learning in the training of deep models, we wonder whether graph-based unsupervised learning can collaboratively boost the performance of semi-supervised learning  ...  , and Young Elite Scientists Sponsorship Program by Tianjin.  ... 
doi:10.1609/aaai.v34i04.5843 fatcat:6nsxdrutsngubko4ii5qpgk6vu

Heuristic Semi-Supervised Learning for Graph Generation Inspired by Electoral College [article]

Chen Li, Xutan Peng, Hao Peng, Jianxin Li, Lihong Wang, Philip S. Yu, Lifang He
2020 arXiv   pre-print
Recently, graph-based algorithms have drawn much attention because of their impressive success in semi-supervised setups.  ...  In all setups tested, our method boosts the average score of base models by a large margin of 4.7 points, as well as consistently outperforms the state-of-the-art.  ...  The so-called graph-based Semi-Supervised Learning (SSL), which holds promise to bootstrap applications even with limited supervision, has therefore attracted increasing research interest.  ... 
arXiv:2006.06469v2 fatcat:vlkw6m4oqnhada44a6un5yhdka

Semi-Supervised Medical Image Classification Based on Attention and Intrinsic Features of Samples

Zhuohao Zhou, Chunyue Lu, Wenchao Wang, Wenhao Dang, Ke Gong
2022 Applied Sciences  
In this paper, based on the consistency strategy, we propose a new semi-supervised model for medical image classification which introduces a self-attention mechanism into the backbone network to learn  ...  Finally, we add a consistency loss similar to the unsupervised consistency loss to encourage the model to learn more about the internal features of unlabeled samples.  ...  Semi-Supervised Learning Based on Consistency Regularization The consistency-based method involves using the information of unlabeled data effectively by making two prediction results for an image consistent  ... 
doi:10.3390/app12136726 fatcat:vkcffxroy5adtkqeh7bdak5csu

Compact Graph based Semi-Supervised Learning for Medical Diagnosis in Alzheimer's Disease

Mingbo Zhao, Rosa H. M. Chan, Tommy W. S. Chow, Peng Tang
2014 IEEE Signal Processing Letters  
In this letter, we introduce a graph based semi-supervised learning algorithm for Medical Diagnosis by using partly labeled samples and large amount of unlabeled samples.  ...  Simulation results show that the proposed method can achieve better sensitivities and specificities compared with other state-of-art graph based semi-supervised learning methods.  ...  Acknowledgments The NACC database was supported by NIA Grant U01 AG016976. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Peng Qiu.  ... 
doi:10.1109/lsp.2014.2329056 pmid:28344434 pmcid:PMC5365156 fatcat:ymnv5ib7prdg7cifu5tfcf3erq

SemiSANet: A Semi-Supervised High-Resolution Remote Sensing Image Change Detection Model Using Siamese Networks with Graph Attention

Chengzhe Sun, Jiangjiang Wu, Hao Chen, Chun Du
2022 Remote Sensing  
To address this limitation, a simple semi-supervised change detection method based on consistency regularization and strong augmentation is proposed in this paper.  ...  First, we construct a Siamese nested UNet with graph attention mechanism (SANet) and pre-train it with a small amount of labeled data.  ...  Semi-Supervised Method Based on Consistency Regularization Semi-supervised learning (SSL) is a branch of deep learning which is conceptually between fully supervised learning and unsupervised learning.  ... 
doi:10.3390/rs14122801 fatcat:4b44tresqbhhdnqot4rhtxihii

Graph-based Semi-Supervised Model for Joint Chinese Word Segmentation and Part-of-Speech Tagging

Xiaodong Zeng, Derek F. Wong, Lidia S. Chao, Isabel Trancoso
2013 Annual Meeting of the Association for Computational Linguistics  
This paper introduces a graph-based semisupervised joint model of Chinese word segmentation and part-of-speech tagging. The proposed approach is based on a graph-based label propagation technique.  ...  Empirical results on Chinese tree bank (CTB-7) and Microsoft Research corpora (MSR) reveal that the proposed model can yield better results than the supervised baselines and other competitive semi-supervised  ...  Graph-based Label Propagation Graph-based label propagation, a critical subclass of semi-supervised learning (SSL), has been widely used and shown to outperform other SSL methods (Chapelle et al., 2006  ... 
dblp:conf/acl/ZengWCT13 fatcat:yoi4aejyufbnxkecas6sykht7e

Unsupervised and semi-supervised learning via ℓ1-norm graph

Feiping Nie, Hua Wang, Heng Huang, Chris Ding
2011 2011 International Conference on Computer Vision  
In this paper, we propose a novel ℓ 1 -norm graph model to perform unsupervised and semi-supervised learning methods.  ...  Instead of minimizing the ℓ 2 -norm of spectral embedding as traditional graph based learning methods, our new graph learning model minimizes the ℓ 1 -norm of spectral embedding with well motivation.  ...  This research was supported by NSF-IIS 1117965, NSF-CCF-0830780, NSF-DMS-0915228, NSF-CCF-0917274.  ... 
doi:10.1109/iccv.2011.6126506 dblp:conf/iccv/NieWHD11 fatcat:2m4pidr6mnbcfnwsz4simnzjla

The GraphNet Zoo: An All-in-One Graph Based Deep Semi-Supervised Framework for Medical Image Classification [article]

Marianne de Vriendt, Philip Sellars, Angelica I Aviles-Rivero
2020 arXiv   pre-print
However, using semi-supervised learning, one can produce accurate classifications using a significantly reduced amount of labelled data.  ...  Therefore, semi-supervised learning is perfectly suited for medical image classification. However, there has almost been no uptake of semi-supervised methods in the medical domain.  ...  The theoretical foundations of SSL has been studied by the community for years. But it is only recently that deep semi-supervised learning has be a focus of great attention.  ... 
arXiv:2003.06451v2 fatcat:nlbxn37yzjgylcuf3kbwlubihm

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

Zhao Zhang, Yan Zhang, Mingliang Xu, Li Zhang, Yi Yang, Shuicheng Yan
2021 arXiv   pre-print
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).  ...  We also introduce the potential application areas of CF-based methods. Finally, we point out some future directions for studying the CF-based representation learning.  ...  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-  ... 
arXiv:2007.15840v3 fatcat:ahun2mogmfapxe4mqhqlsakyku

CLASSIFICATION BASED ON SEMI-SUPERVISED LEARNING: A REVIEW

Aska Ezadeen Mehyadin, Adnan Mohsin Abdulazeez
2021 Iraqi Journal for Computers and Informatics  
By utilizing a large number of unsupervised inputs along with the supervised inputs, the semi-supervised learning solves this issue, to create a good training sample.  ...  Semi-supervised learning is the class of machine learning that deals with the use of supervised and unsupervised learning to implement the learning process.  ...  Fig. 7 : 7 Fig.7: Graph-Based Method Fig. 8 : 8 Fig. 8: mincut TABLE 1 COMPARISON 1 CLASSIFICATION BASED ON SEMI-SUPERVISED LEARNING Ref.  ... 
doaj:19f0153a03af451f84c46af0cd0ee293 fatcat:odysp4pyufc4xcz366chcqloae

Semi-supervised Adversarial Active Learning on Attributed Graphs [article]

Yayong Li, Jie Yin, Ling Chen
2019 arXiv   pre-print
as already labelled, and a semi-supervised discriminator network that distinguishes the unlabelled from the existing labelled nodes in the latent space.  ...  In this paper, we propose a SEmi-supervised Adversarial active Learning (SEAL) framework on attributed graphs, which fully leverages the representation power of deep neural networks and devises a novel  ...  Field and Harmonic Function (GFHF) based method [6] , Learning with Local and Global Consistency (LLGC) based methods [7] , Label Propagation (LP) based methods [28] .  ... 
arXiv:1908.08169v1 fatcat:i2olskc7vvcodeqzsgyfvpctue

Select and Calibrate the Low-confidence: Dual-Channel Consistency based Graph Convolutional Networks [article]

Shuhao Shi, Jian Chen, Kai Qiao, Shuai Yang, Linyuan Wang, Bin Yan
2022 arXiv   pre-print
Previous studies in Semi-Supervised Learning (SSL) for graph have focused on using network predictions to generate soft pseudo-labels or instructing message propagation, which inevitably contains the incorrect  ...  and high-confidence samples selection based on dual-channel consistency.  ...  Acknowledgements This work was supported by the National Key R&D Program of China under Grant No. 2017YFB1002502.  ... 
arXiv:2205.03753v1 fatcat:sycvxs6w2vb5xinjlbjbrjucpi
« Previous Showing results 1 — 15 out of 7,067 results