Timezone: »

Log-Hilbert-Schmidt metric between positive definite operators on Hilbert spaces
Minh Ha Quang · Marco San Biagio · Vittorio Murino

This paper introduces a novel mathematical and computational framework, namely {\it Log-Hilbert-Schmidt metric} between positive definite operators on a Hilbert space. This is a generalization of the Log-Euclidean metric on the Riemannian manifold of positive definite matrices to the infinite-dimensional setting. The general framework is applied in particular to compute distances between covariance operators on a Reproducing Kernel Hilbert Space (RKHS), for which we obtain explicit formulas via the corresponding Gram matrices. Empirically, we apply our formulation to the task of multi-category image classification, where each image is represented by an infinite-dimensional RKHS covariance operator. On several challenging datasets, our method significantly outperforms approaches based on covariance matrices computed directly on the original input features, including those using the Log-Euclidean metric, Stein and Jeffreys divergences, achieving new state of the art results.

Author Information

Minh Ha Quang (RIKEN Center for Advanced Intelligence Project)
Vittorio Murino (Istituto Italiano di Tecnologia)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors