Random Fourier Approximations for Skewed Multiplicative Histogram Kernels

By Fuxin Li, Catalin Ionescu, Cristian Sminchisescu. 2010

73 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Quasi-Monte Carlo Feature Maps for Shift-Invariant Kernels (2014, background): “Li et al. [2010] use Bochner’s theorem to provide random features to the wider class of group-invariant kernels.”
Random Feature Maps for Dot Product Kernels (2012, background): “Subsequently Li et al. (2010) generalized this to a larger class of group invariant kernels while still invoking Bochner’s theorem.”
Orthogonal Random Features (2016, background): “2 Related Works Explicit nonlinear random feature maps have been constructed for many types of kernels, such as intersection kernels [15], generalized RBF kernels [22], skewed multiplicative histogram kernels [14], additive kernels [24], and polynomial kernels [11, 18].”
Random Laplace Feature Maps for Semigroup Kernels on Histograms (2014, background): “[15] suggest approximate feature maps for “skewed” multiplicative variants of the Intersection and χ(2) kernels, in an attempt to match the empirical performance of the exponentiated-χ(2) kernel, considered state of the art [3] for histogram descriptors.”
Linear-Time Learning on Distributions with Approximate Kernel Embeddings (2015, methodology): “To the best of our knowledge, this work provides the ﬁrst non-discretized embedding for non-L 2 kernels for probability density functions.”
CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts (2012, methodology): “Here, we handle one of these similarity functions with linear regression by first applying a randomized feature map to linearly approximate the Laplacian-RBF kernel [77], [78].”
Constrained parametric min-cuts for automatic object segmentation (2010, methodology): “Some of these similarity functions can nevertheless be handled with linear regressi on, by first applying a randomized feature map that approximates the Laplacian-RBF kernel [72], [73].”
Spherical Random Features for Polynomial Kernels (2015, background): “Explicit nonlinear random feature maps have also been proposed for other types of kernels, such as intersection kernels [7], generalized RBF kernels [8], skewed multiplicative histogram kernels [9], additive kernels [10], and semigroup kernels [11].”
Probabilistic Joint Image Segmentation and Labeling (2011, methodology): “Each of the feature vectors is transformed using a rand omized feature map that approximates the Gaussian-RBF kernel [26, 27].”
Latent structured models for human pose estimation (2011, methodology): “Random Fourier approximations (RF) [18, 26, 16] provide an efficient methodology to create explicit feature transforms for non-linear kernel methods.”
Compact Random Feature Maps (2013, background): “Besides (Rahimi & Recht, 2007), there have been several approaches proposed to approximate other kernels such as group invariant (Li et al., 2010), intersection (Maji & Berg, 2009), and RBF kernels (Vempati et al., 2010).”
Object Recognition by Sequential Figure-Ground Ranking (2011, methodology): “This result is not included in this paper because the methodology is slightly different, but see our work in Li et al. (2010a) for details.”