Logo eprints

Rotation-Invariant Restricted Boltzmann Machine Using Shared Gradient Filters

Giuffrida, Mario Valerio and Tsaftaris, Sotirios A. Rotation-Invariant Restricted Boltzmann Machine Using Shared Gradient Filters. In: Artificial Neural Networks and Machine Learning – ICANN 2016 25th. International Conference on Artificial Neural Networks, Barcelona, Spain, September 6-9, 2016, Proceedings, Part II. Lecture Notes in Computer Science (9887). Springer International Publishing, pp. 480-488. ISBN 978-3-319-44780-3 (2016)

Full text not available from this repository.

Abstract

Finding suitable features has been an essential problem in computer vision. We focus on Restricted Boltzmann Machines (RBMs), which, despite their versatility, cannot accommodate transformations that may occur in the scene. As a result, several approaches have been proposed that consider a set of transformations, which are used to either augment the training set or transform the actual learned filters. In this paper, we propose the Explicit Rotation-Invariant Restricted Boltzmann Machine, which exploits prior information coming from the dominant orientation of images. Our model extends the standard RBM, by adding a suitable number of weight matrices, associated with each dominant gradient. We show that our approach is able to learn rotation-invariant features, comparing it with the classic formulation of RBM on the MNIST benchmark dataset. Overall, requiring less hidden units, our method learns compact features, which are robust to rotations.

Item Type: Book Section
Identification Number: https://doi.org/10.1007/978-3-319-44781-0_57
Subjects: Q Science > QA Mathematics > QA76 Computer software
T Technology > T Technology (General)
Research Area: Computer Science and Applications
Depositing User: Caterina Tangheroni
Date Deposited: 14 Nov 2016 11:18
Last Modified: 14 Nov 2016 11:18
URI: http://eprints.imtlucca.it/id/eprint/3594

Actions (login required)

Edit Item Edit Item