14,802 Hits in 4.3 sec

Semi-supervised Discriminant Analysis

Deng Cai, Xiaofei He, Jiawei Han
2007 2007 IEEE 11th International Conference on Computer Vision  
Linear Discriminant Analysis (LDA) has been a popular method for extracting features which preserve class separability.  ...  In this paper, we propose a novel method, called Semisupervised Discriminant Analysis (SDA), which makes use of both labeled and unlabeled samples.  ...  In this paper, we aim at dimensionality reduction in the semi-supervised case. We proposed a semi-supervised dimensionality reduction algorithm, called Semi-supervised Discriminant Analysis (SDA).  ... 
doi:10.1109/iccv.2007.4408856 dblp:conf/iccv/CaiHH07a fatcat:amnu2w4yvneadg5q6i6vwpssi4

Complex Moment-Based Supervised Eigenmap for Dimensionality Reduction

Akira Imakura, Momo Matsuda, Xiucai Ye, Tetsuya Sakurai
Herein, to overcome the deficiency of the information loss, we propose a novel complex moment-based supervised eigenmap including multiple eigenvectors for dimensionality reduction.  ...  Dimensionality reduction methods that project highdimensional data to a low-dimensional space by matrix trace optimization are widely used for clustering and classification.  ...  JPMJPR16U6), the New Energy and Industrial Technology Development Organization (NEDO) and the Japan Society for the Promotion of Science (JSPS), Grants-in-Aid for Scientific Research (Nos. 17K12690, 18H03250  ... 
doi:10.1609/aaai.v33i01.33013910 fatcat:oxmbkotkxnfwjcnv5h5xyfofjy

Local Fisher Discriminant Analysis for Pedestrian Re-identification

Sateesh Pedagadi, James Orwell, Sergio Velastin, Boghos Boghossian
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
A second stage further reduces the dimensionality, using a Local Fisher Discriminant Analysis defined by a training set.  ...  A first processing stage performs unsupervised PCA dimensionality reduction, constrained to maintain the redundancy in color-space representation.  ...  Supervised Dimensionality Reduction The second stage uses a supervised dimensionality reduction method to estimate a lower dimensional embedding space into which x i may be transformed.  ... 
doi:10.1109/cvpr.2013.426 dblp:conf/cvpr/PedagadiOVB13 fatcat:cb22mbwcmvezfourizil6fvlb4

Significance of Dimensionality Reduction in Image Processing

Shereena V. B, Julie M. David
2015 Signal & Image Processing An International Journal  
The aim of this paper is to present a comparative study of two linear dimension reduction methods namely PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis).  ...  PCA finds the axes with maximum variance for the whole data set where LDA tries to find the axes for best class seperability.  ...  The most popular among the Dimensionality Reduction Algorithms are Principal Component Analysis and Linear Discriminant Analysis.  ... 
doi:10.5121/sipij.2015.6303 fatcat:calbiutzjngtpopakc6yyrpfci

Semi-supervised optimization algorithm basedon Laplacian Eigenmaps

2020 North atlantic university union: International Journal of Circuits, Systems and Signal Processing  
As a member of many dimensionalityreduction algorithms, manifold learning is the hotspot ofrecent dimensionality reduction algorithm.  ...  The experimental results show thatthis semi-supervised method does well in classifying.  ...  Linear discriminant analysis is similar to the principal component analysis method. It projects high-dimensional pattern samples into the best discriminant vector space.  ... 
doi:10.46300/9106.2020.14.62 fatcat:l6k5ycr2abanvhmnakrgnedyhe

Classification of Hyperspectral Images Based on Supervised Sparse Embedded Preserving Projection

Fen Cai, Miao-Xia Guo, Li-Fang Hong, Ying-Yi Huang
2019 Applied Sciences  
Dimensionality reduction is an important research area for hyperspectral remote sensing images due to the redundancy of spectral information.  ...  In order to solve this problem, this paper proposes a dimensionality reduction algorithm called the supervised sparse embedded preserving projection (SSEPP) algorithm.  ...  (b) (c) (d) (e) Conclusions This paper presented a supervised sparse embedded preserving projection (SSEPP) dimensionality reduction algorithm for hyperspectral images; it is an extension of SPP.  ... 
doi:10.3390/app9173583 fatcat:4a5ok2gitfdzdmskzj3gtjsjhq

Supervised dimensionality reduction for big data

Joshua T. Vogelstein, Eric W. Bridgeford, Minh Tang, Da Zheng, Christopher Douville, Randal Burns, Mauro Maggioni
2021 Nature Communications  
We introduce an approach to extending principal components analysis by incorporating class-conditional moment estimates into the low-dimensional projection.  ...  There is a lack of interpretable supervised dimensionality reduction methods that scale to millions of dimensions with strong statistical theoretical guarantees.  ...  onto the low-dimensional space, a requirement for supervised learning.  ... 
doi:10.1038/s41467-021-23102-2 pmid:34001899 fatcat:gyc7psyekzc65nsqwcj5zi33ku

Semi-Supervised Linear Discriminant Clustering

Chien-Liang Liu, Wen-Hoar Hsaio, Chia-Hoang Lee, Fu-Sheng Gou
2014 IEEE Transactions on Cybernetics  
The proposed algorithm considers clustering and dimensionality reduction simultaneously by connecting K-means and linear discriminant analysis (LDA).  ...  Index Terms-Clustering, linear discriminant analysis, semi-supervised learning, soft label, text mining.  ...  We propose a method called semisupervised linear discriminant clustering (Semi-LDC), which connects K-means and linear discriminant analysis (LDA), to consider clustering and dimensionality reduction simultaneously  ... 
doi:10.1109/tcyb.2013.2278466 pmid:23996591 fatcat:dpxxp6lcyraxhb2rzrbryy2pqa

Texture Based Hyperspectral Image Classification

B. Kumar, O. Dikshit
2014 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
This research work presents a supervised classification framework for hyperspectral data that takes into account both spectral and spatial information.  ...  Texture analysis is performed to model spatial characteristics that provides additional information, which is used along with rich spectral measurements for better classification of hyperspectral imagery  ...  Two techniques, one supervised and one unsupervised were employed for spectral feature reduction.  ... 
doi:10.5194/isprsarchives-xl-8-793-2014 fatcat:2nxol5lgcndhlci6pna5ebviiy

High-Dimensional Discriminant Analysis

Charles Bouveyron, Stéphane Girard, Cordelia Schmid
2007 Communications in Statistics - Theory and Methods  
We propose a new method of discriminant analysis, called High Dimensional Discriminant Analysis (HHDA).  ...  Thus, HDDA reduces the dimension for each class independently and regularizes class conditional covariance matrices in order to adapt the Gaussian framework to high dimensional data.  ...  Introduction In this paper, we introduce a new method of discriminant analysis, called High Dimensional Discriminant analysis (HDDA) to classify high dimensional data, as occur for example in visual object  ... 
doi:10.1080/03610920701271095 fatcat:etunz6f53bcptn7lc6p4m44blq

Quantile-Quantile Embedding for distribution transformation and manifold embedding with ability to choose the embedding distribution

Benyamin Ghojogh, Fakhri Karray, Mark Crowley
2021 Machine Learning with Applications  
It can also be used for modifying the embedding distribution of other dimensionality reduction methods, such as PCA, t-SNE, and deep metric learning, for better representation or visualization of data.  ...  Embedding Distribution in Manifold Learning Methods Some manifold learning and dimensionality reduction methods make an assumption about the distribution of neighbors of data points.  ...  Note that QQE for manifold learning can be supervised regardless of whether the dimensionality reduction method used for initialization is unsupervised or supervised.  ... 
doi:10.1016/j.mlwa.2021.100088 fatcat:jzwwj3ruxbexpalfzrad77ssja

Semisupervised Kernel Marginal Fisher Analysis for Face Recognition

Ziqiang Wang, Xia Sun, Lijun Sun, Yuchun Huang
2013 The Scientific World Journal  
To effectively cope with this problem, a novel dimensionality reduction algorithm called semisupervised kernel marginal Fisher analysis (SKMFA) for face recognition is proposed in this paper.  ...  SKMFA can make use of both labelled and unlabeled samples to learn the projection matrix for nonlinear dimensionality reduction.  ...  To this end, principal component analysis (PCA) and linear discriminant analysis (LDA) [1] are the most well-known dimensionality reduction techniques.  ... 
doi:10.1155/2013/981840 pmid:24163638 pmcid:PMC3791838 fatcat:fpynhn4ohnhtbcoqhu3frv45bu

Gaussian beam velocity tomography based on azimuth-opening angle domain common imaging gathers

Jiexiong Cai, Hao Zheng
2019 Journal of Geophysics and Engineering  
(b) (c) (d) (e) Conclusions This paper presented a supervised sparse embedded preserving projection (SSEPP) dimensionality reduction algorithm for hyperspectral images; it is an extension of SPP.  ...  The common DR algorithms mainly include principal component analysis (PCA) [6] and liner discriminative analysis (LDA) [7] .  ... 
doi:10.1093/jge/gxz061 fatcat:2yw46oopifc3xewcacw4onlcsq

A unified dimensionality reduction framework for semi-paired and semi-supervised multi-view data

Xiaohong Chen, Songcan Chen, Hui Xue, Xudong Zhou
2012 Pattern Recognition  
Based on the framework, we develop a novel dimensionality reduction method, termed as semi-paired and semi-supervised generalized correlation analysis (S 2 GCA).  ...  In this paper, we present a general dimensionality reduction framework for semi-paired and semi-supervised multi-view data which naturally generalizes existing related works by using different kinds of  ...  SCCA is finally devised by such two CCAs together. x y x y … Semi-paired and semi-supervised dimensionality reduction (S 2 DR): a general dimensionality reduction framework for multi-view data Up to  ... 
doi:10.1016/j.patcog.2011.11.008 fatcat:zh6vvnnvazfghkbvqiwn3xtrwm

Local Fisher discriminant analysis for supervised dimensionality reduction

Masashi Sugiyama
2006 Proceedings of the 23rd international conference on Machine learning - ICML '06  
Traditional Fisher discriminant analysis is a popular and powerful method for this purpose.  ...  In this paper, we propose a new dimensionality reduction method called local Fisher discriminant analysis (LFDA), which is a localized variant of Fisher discriminant analysis.  ...  He also acknowledges financial support from MEXT (Grant-in-Aid for Young Scientists 17700142).  ... 
doi:10.1145/1143844.1143958 dblp:conf/icml/Sugiyama06 fatcat:g7voda6aszf4hkwglphxpr5mp4
« Previous Showing results 1 — 15 out of 14,802 results