Open AccessProceedings Article
A Kullback-Leibler Divergence Based Kernel for SVM Classification in Multimedia Applications
Pedro J. Moreno,Purdy Ho,Nuno Vasconcelos +2 more
- Vol. 16, pp 1385-1392
Reads0
Chats0
TLDR
This paper suggests an alternative procedure to the Fisher kernel for systematically finding kernel functions that naturally handle variable length sequence data in multimedia domains and derives a kernel distance based on the Kullback-Leibler (KL) divergence between generative models.Abstract:
Over the last years significant efforts have been made to develop kernels that can be applied to sequence data such as DNA, text, speech, video and images. The Fisher Kernel and similar variants have been suggested as good ways to combine an underlying generative model in the feature space and discriminant classifiers such as SVM's. In this paper we suggest an alternative procedure to the Fisher kernel for systematically finding kernel functions that naturally handle variable length sequence data in multimedia domains. In particular for domains such as speech and images we explore the use of kernel functions that take full advantage of well known probabilistic models such as Gaussian Mixtures and single full covariance Gaussian models. We derive a kernel distance based on the Kullback-Leibler (KL) divergence between generative models. In effect our approach combines the best of both generative and discriminative methods and replaces the standard SVM kernels. We perform experiments on speaker identification/verification and image classification tasks and show that these new kernels have the best performance in speaker verification and mostly outperform the Fisher kernel based SVM's and the generative classifiers in speaker identification and image classification.read more
Citations
More filters
Proceedings ArticleDOI
The pyramid match kernel: discriminative classification with sets of image features
Kristen Grauman,Trevor Darrell +1 more
TL;DR: A new fast kernel function is presented which maps unordered feature sets to multi-resolution histograms and computes a weighted histogram intersection in this space and is shown to be positive-definite, making it valid for use in learning algorithms whose optimal solutions are guaranteed only for Mercer kernels.
Journal ArticleDOI
Support vector machines using GMM supervectors for speaker verification
TL;DR: This work examines the idea of using the GMM supervector in a support vector machine (SVM) classifier and proposes two new SVM kernels based on distance metrics between GMM models that produce excellent classification accuracy in a NIST speaker recognition evaluation task.
Journal ArticleDOI
Iterative Weighted Maximum Likelihood Denoising With Probabilistic Patch-Based Weights
TL;DR: The proposed filter is an extension of the nonlocal means (NL means) algorithm introduced by Buades, which performs a weighted average of the values of similar pixels which depends on the noise distribution model.
Proceedings ArticleDOI
SVM Based Speaker Verification using a GMM Supervector Kernel and NAP Variability Compensation
TL;DR: A support vector machine kernel is constructed using the GMM supervector and similarities based on this kernel between the method of SVM nuisance attribute projection (NAP) and the recent results in latent factor analysis are shown.
Journal Article
Probability Product Kernels
TL;DR: The advantages of discriminative learning algorithms and kernel machines are combined with generative modeling using a novel kernel between distributions to exploit the properties, metrics and invariances of the generative models the authors infer from each datum.
References
More filters
Statistical learning theory
TL;DR: Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
Journal ArticleDOI
Support vector machines for histogram-based image classification
TL;DR: It is observed that a simple remapping of the input x(i)-->x(i)(a) improves the performance of linear SVM's to such an extend that it makes them, for this problem, a valid alternative to RBF kernels.
Proceedings Article
Using the Fisher Kernel Method to Detect Remote Protein Homologies
TL;DR: A new method, called the Fisher kernel method, for detecting remote protein homologies is introduced and shown to perform well in classifying protein domains by SCOP superfamily.
Proceedings ArticleDOI
Support vector machines for speaker verification and identification
Vincent Wan,William M. Campbell +1 more
TL;DR: A new technique for normalising the polynomial kernel is developed and used to achieve performance comparable to other classifiers on the YOHO database.
Journal ArticleDOI
Second-order statistical measures for text-independent speaker identification
TL;DR: The use of some of the proposed measures as a reference benchmark to evaluate the intrinsic complexity of a given database under a given protocol is suggested as a conclusion to this work.