<html>
<body>
<p>We introduce a new discriminative learning method for image classification.
We assume that the images are represented <br/>
by unordered, multi-dimensional, finite sets of feature vectors, and that these
sets might have different cardinality. <br/>
By means of consistent nonparametric divergence estimators we define new kernels
over these sets, and then apply them in kernel classifiers. <br/>
We assume that the images are represented by unordered, multi-dimensional,
finite sets of feature vectors, and that these sets might have different
cardinality. By means of consistent nonparametric divergence estimators we
define new kernels over these sets, and then apply them in kernel classifiers.
Our numerical results demonstrate that in many cases this approach can
outperform state-of-the-art competitors on both simulated and challenging
real-world datasets</p>
real-world datasets.</p>
</body>
</html>
<html>
<body>
<p><a href="../../../../19607.html">Barnabas Poczos,</a>
<a href="../../../../18596.html">Liang Xiong</a>,
<a href="../../../../20597.html">Dougal J. Sutherland</a>,
<a href="../../../../10230.html">Jeff Schneider</a></p>
<p><a href="daisy:19607">Barnabas
Poczos</a><a href="../../../../19607.html">,</a> <a href="daisy:18596">Liang
Xiong</a>,<a href="daisy:20597"> Dougal J. Sutherland</a>,
<a href="daisy:10230">Jeff Schneider</a></p>
</body>
</html>