Filters








7,881 Hits in 6.0 sec

Robust Semi-supervised Learning for Biometrics [chapter]

Nanhai Yang, Mingming Huang, Ran He, Xiukun Wang
2010 Lecture Notes in Computer Science  
To deal with the problem of sensitivity to noise in semi-supervised learning for biometrics, this paper proposes a robust Gaussian-Laplacian Regularized (GLR) framework based on maximum correntropy criterion  ...  Experimental results show that the proposed GRL-MCC can effectively improve the semi-supervised learning performance and is robust to mislabeling noise and occlusion as compared with GLR.  ...  Experimental results illustrate that GLR-MCC is robust against training noise for both images and labels. Conclusion In this paper, we propose a novel robust GLR-MCC framework based on MCC.  ... 
doi:10.1007/978-3-642-15621-2_51 fatcat:jmzg7wbctrfcncm2u24hh4cqmu

Robust Variational Autoencoder [article]

Haleh Akrami, Anand A. Joshi, Jian Li, Sergul Aydore, Richard M. Leahy
2019 arXiv   pre-print
We demonstrate the performance of our β-divergence based autoencoder for a range of image datasets, showing improved robustness to outliers both qualitatively and quantitatively.  ...  Machine learning methods often need a large amount of labeled training data.  ...  Conclusion and Discussion The presence of outliers in the form of noise, mislabeled data, and anomalies can impact the performance of machine learning models for labeling and anomaly detection tasks.  ... 
arXiv:1905.09961v2 fatcat:wsiny2pjqndpva6zpxtvhexbte

From Photo Streams to Evolving Situations [article]

Mengfan Tang, Feiping Nie, Siripen Pongpaichet, Ramesh Jain
2017 arXiv   pre-print
To overcome the noisy data which degrades graph quality, leading to poor recognition results, we take advantage of two kinds of noise-robust norms which can eliminate the adverse effects of outliers in  ...  To extend the method for unknown situations, we introduce a soft label method which enables the traditional semi-supervised learning framework to accurately predict predefined labels as well as effectively  ...  Noise Robust Semi-Supervised Learning Methods for Unknown Labels Traditional methods such as (1) are built on 2 -norm of graph embedding.  ... 
arXiv:1702.05878v1 fatcat:ihp4ifghzfbkhg4bvokbboytfm

l2, 1 Regularized correntropy for robust feature selection

Ran He, Tieniu Tan, Liang Wang, Wei-Shi Zheng
2012 2012 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper, we study the problem of robust feature extraction based on 2,1 regularized correntropy in both theoretical and algorithmic manner.  ...  Extensive experiments show that our method can select robust and sparse features, and outperforms several state-of-the-art subspace methods on largescale and open face recognition datasets.  ...  Since discriminative LPP is based on a local structure which depends on label information, it is sensitive to mislabeling noise.  ... 
doi:10.1109/cvpr.2012.6247966 dblp:conf/cvpr/HeTWZ12 fatcat:b2cafx7n7ngndnie4g4drfg7ue

Learning Hybrid Representation by Robust Dictionary Learning in Factorized Compressed Space [article]

Jiahuan Ren, Zhao Zhang, Sheng Li, Yang Wang, Guangcan Liu, Shuicheng Yan, Meng Wang
2019 arXiv   pre-print
Specifically, J-RFDL performs the robust representation by DL in a factorized compressed space to eliminate the negative effects of noise and outliers on the results, which can also make the DL process  ...  The setting of J-RFDL aims at improving the data representations by enhancing the robustness to outliers and noise in data, encoding the reconstruction error more accurately and obtaining hybrid salient  ...  ACKNOWLEDGMENT The authors would like to express sincere thanks to reviewers for their insightful comments, making our manuscript a higher standard.  ... 
arXiv:1912.11785v1 fatcat:ibteex7jqfao3e6kejsdna6kzq

Semantic clusters based manifold ranking for image retrieval

Ran Chang, Xiaojun Qi
2011 2011 18th IEEE International Conference on Image Processing  
Specifically, we apply the SVM-based relevance feedback technique to create semantic clusters for computing the reliability score of each database image.  ...  Our system ensures to propagate the labels in the relevance vector to the images with high reliability scores and discriminately spread the ranking scores of positive and negative images via the weighted  ...  This noise resilience feature mainly results from the robust, meaningful SCs and their reliable backbone images learned in the training process.  ... 
doi:10.1109/icip.2011.6116133 dblp:conf/icip/ChangQ11 fatcat:bfenevvchrcevhlanmxzhwocle

A Regularized Correntropy Framework for Robust Pattern Recognition

Ran He, Wei-Shi Zheng, Bao-Gang Hu, Xiang-Wei Kong
2011 Neural Computation  
Then an l 1 regularization scheme is imposed on the correntropy to learn robust and sparse representations.  ...  Second, we develop a new correntropy-based classifier based on the learned regularization scheme for robust object recognition.  ...  Acknowledgments Thanks to Christian Ocier for proofreading this manuscript. We also greatly thank the associate editor and the reviewers for their valuable comments and advice.  ... 
doi:10.1162/neco_a_00155 fatcat:pdsqxtalejd25jm6b3irl4a2ja

MembershipMap: data transformation cased on membership aggregation

H. Frigui
2004 Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.  
Since sub-concept labels are prone to uncertainty inherent in the original data and in the initial extraction process, a combination of labeling schemes that are based on different measures of uncertainty  ...  We show that the MembershipMap can be used as a flexible pre-processing tool to support such tasks as: sampling, data cleaning, and outlier detection.  ...  5) Identifying Noise Points and Outliers Noise and outlier detection is a challenging problem.  ... 
doi:10.1109/icpr.2004.1334261 dblp:conf/icpr/Frigui04 fatcat:ian4ohianbadnbz3vymptcnxvm

Maximum Correntropy Criterion for Robust Face Recognition

Ran He, Wei-Shi Zheng, Bao-Gang Hu
2011 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In this paper, we present a sparse correntropy framework for computing robust sparse representations of face images for recognition.  ...  Compared with the state-of-the-art l 1 norm-based sparse representation classifier (SRC), which assumes that noise also has a sparse representation, our sparse algorithm is developed based on the maximum  ...  ACKNOWLEDGMENTS The authors would like to greatly thank the associate editor and the reviewers for their valuable comments and advice.  ... 
doi:10.1109/tpami.2010.220 pmid:21135440 fatcat:leuk4exutfdx5kns3uizvjs44e

Density-based clustering of static and dynamic functional MRI connectivity features obtained from subjects with cognitive impairment

D. Rangaprakash, Alzheimer's Disease Neuroimaging Initiative, Toluwanimi Odemuyiwa, D. Narayana Dutt, Gopikrishna Deshpande
2020 Brain Informatics  
To assess the robustness of clustering to noise/outliers, we propose a novel method called recursive-clustering using additive-noise (R-CLAN).  ...  Results demonstrated that both clustering algorithms were effective, although OPTICS with dynamic connectivity features outperformed in terms of cluster purity (95.46%) and robustness to noise/outliers  ...  ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer's Association  ... 
doi:10.1186/s40708-020-00120-2 pmid:33242116 fatcat:ciw3vscdjzf7jflpm2r4snn54q

Deep Classifiers from Image Tags in the Wild

Hamid Izadinia, Bryan C. Russell, Ali Farhadi, Matthew D. Hoffman, Aaron Hertzmann
2015 Proceedings of the 2015 Workshop on Community-Organized Multimodal Mining: Opportunities for Novel Solutions - MMCommons'15  
We introduce a large-scale robust classification algorithm, in order to handle the inherent noise in these tags, and a calibration procedure to better predict objective annotations.  ...  This paper proposes direct learning of image classification from image tags in the wild, without filtering. Each wild tag is supplied by the user who shared the image online.  ...  Since tag noise is different for different tags, the tag outlier probabilities are learned simultaneously with the classifier weights.  ... 
doi:10.1145/2814815.2814821 dblp:conf/mm/IzadiniaRFHH15 fatcat:hs5ouvy5hvgsnkhz3ftyqa4uzq

Active Concept Learning in Image Databases

A. Dong, B. Bhanu
2005 IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)  
Experimental results on Corel database show the efficacy of our active concept learning approach and the improvement in retrieval performance by concept transduction.  ...  To achieve concept learning, we a) propose a new user directed semi-supervised expectation-maximization algorithm for mixture parameter estimation, and b) develop a novel model selection method based on  ...  the noise. 2) Real Data: We implement our concept learning approach on this database with , and .  ... 
doi:10.1109/tsmcb.2005.846653 pmid:15971914 fatcat:prrpcpeqh5gbtfqpeecrsyjyti

Automatic Image Annotation using Possibilistic Clustering Algorithm

Mohamed Maher Ben Ismail, Sara N. Alfaraj, Ouiem Bchir
2019 International Journal of Fuzzy Logic and Intelligent Systems  
Besides, the unsupervised learning task exploits the robustness to noise of a possibilistic clustering algorithm, and generates membership degrees that represent the typicality of image regions with respect  ...  distribution of textual keywords and images.  ...  Acknowledgements The authors are grateful for the support by the Research Center of the College of Computer and Information Sciences, King Saud University.  ... 
doi:10.5391/ijfis.2019.19.4.250 fatcat:nli6zyseyjb6ro53pppq4ryynu

Guide-Wire Extraction through Perceptual Organization of Local Segments in Fluoroscopic Images [chapter]

Nicolas Honnorat, Régis Vaillant, Nikos Paragios
2010 Lecture Notes in Computer Science  
Komodakis for providing the clustering method.  ...  In cardiac angioplasty, the problem is particularly challenging due to the following reasons: (i) low signal to noise ratio, (ii) the use of 2D images that accumulate information from the whole volume,  ...  Experimental Validation Experiments were carried out on a database of 15 sequences of 10 images 1000x1000 acquired during interventions on 13 patients with a frame rate of 15 images per second, where clinical  ... 
doi:10.1007/978-3-642-15711-0_55 fatcat:fj7lxtzoavay3jzt3yva3jl3qm

High-accuracy classification of attention deficit hyperactivity disorder with l2,1-norm linear discriminant analysis and binary hypothesis testing

Yibin Tang, Xufei Li, Ying Chen, Yuan Zhong, Aimin Jiang, Chun Wang
2020 IEEE Access  
The FCs of test data (without seeing its label) are used for training and thus affect the subspace learning of training data under binary hypotheses.  ...  ., insufficient data and noise disturbance.  ...  Meanwhile, an l 2,1 -norm LDA model is employed for the robust feature learning to alleviate noise disturbance.  ... 
doi:10.1109/access.2020.2982401 fatcat:gnbejssuzrbnfpgkn7j3pglvcq
« Previous Showing results 1 — 15 out of 7,881 results