Bilinear Classifiers for Visual Recognition

December 2009

Bilinear Classifiers for Visual Recognition

Authors:

Hamed Pirsiavash, Deva Ramanan, and Charless C. Fowlkes
Conference Paper
Proceedings of (NeurIPS) Neural Information Processing Systems

Abstract:

We describe an algorithm for learning bilinear SVMs. Bilinear classifiers are a discriminative variant of bilinear models, which capture the dependence of data on multiple factors. Such models are particularly appropriate for visual data that is better represented as a matrix or tensor, rather than a vector. Matrix encod- ings allow for more natural regularization through rank restriction. For example, a rank-one restriction produces a bilinear classifier that can be interpreted as a sep- arable filter. We also use bilinear classifiers for transfer learning by sharing linear factors between different tasks. Finally, we show that bilinear classifiers can be trained with biconvex programs. Such programs are optimized with coordinate descent, where each step is equivalent to a standard convex problem. This allows us to leverage existing SVM solvers during learning. We demonstrate bilinear SVMs on difficult problems of people detection in video sequences and action classification of video sequences, achieving state-of-the-art results in both.
@conference{Pirsiavash-2009-121221,
author = {Hamed Pirsiavash And Deva Ramanan And Charless C. Fowlkes},
title = {Bilinear Classifiers for Visual Recognition},
booktitle = {Proceedings of (NeurIPS) Neural Information Processing Systems},
year = {2009},
month = {December},
pages = {1482 – 1490},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.