Improving SVM accuracy by training on auxiliary data sources

By Pengcheng Wu, Thomas G. Dietterich. 2004

325 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Plant Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Plant Science

Citations in the corpus

Learning with Augmented Features for Heterogeneous Domain Adaptation (2012, methodology): “used for diﬀerent research ﬁelds such as natural language processing and computer vision (Blitzer et al., 2006; 2007; Daum´e III, 2007; Duan et al., 2010; 2012b;a; Wu & Dietterich, 2004).”
Topic-bridged PLSA for cross-domain text classification (2008, methodology): “[21] proposed an SVM-based algorithm using both base and auxiliary training data.”
Transfer learning for cross-company software defect prediction (2012, background): “Transfer learning technique also works well on many fields such as image classification [19], name-entity recognition [20], web page translation [21], natural language processing [22], and email spam filtering [23].”
A Survey on Transfer Learning (2010, background): “Wu and Dietterich [53] integrated the source domain (auxiliary) data an Support Vector Machine (SVM) framework for improving the classification performance.”
Machine Learning Paradigms for Speech Recognition: An Overview (2013, unknown): “In [116], [186], [187], the”
Self-taught clustering (2008, methodology): “Wu and Dietterich(2004)investigatedmethodsforimproving SVMclassi.erswithauxiliary training data sources.”
Transferring Naive Bayes Classifiers for Text Classification (2007, unknown): “Wu & Dietterich (2004) proposed a classi-ﬁcation algorithm using both inadequate training data and large amount of low quality auxiliary data.”
Generalization Bounds for Domain Adaptation (2012, background): “Meanwhile, we discuss the factors that affect the asymptotic behavior of the learning process and the numerical experiments support our theoretical findings as well.”
A Regularization Approach to Learning Task Relationships in Multitask Learning (2014, methodology): “For example, the model in Wu and Dietterich [2004] can only handle the situation that m = 1 , but our method can handle the situations m = 1 and m > 1 in a uniﬁed framework.”
Logistic regression with an auxiliary data source (2005, background): “A related problem has been studied in [Wu & Dietterich , 2004], where the classifier is trained on two fixed and labeled data sets D p and D a , where D a is of lower quality and provides weaker evidence for the classifier design.”
Cross-domain video concept detection using adaptive svms (2007, background): “While the mismatch between training and testing distribution is a fundamental problem in machine learning [5, 17, 18], it is particularly severe in the multimedia area due to the large data variance and the “semantic gap” between content and semantics.”
Domain Transfer SVM for video concept detection (2009, methodology): “However, all these methods [5, 7, 17, 20] did not utilize unlabeled patterns in the target domain.”
Safety in numbers: Learning categories from few examples with multi model knowledge transfer (2010, background): “Wu and Dietterich transferred source training examples either as support vectors or as constraints (or both) and demonstrated improved image classification by SVMs [24].”
Learning from Multiple Sources (2006, background): “Wu and Dietterich studied similar problems experimentally in the context of SVMs [2].”