Multi-Level Sensor Fusion with Deep Learning - Archive ouverte HAL Access content directly
Journal Articles IEEE Sensors Letters Year : 2018

Multi-Level Sensor Fusion with Deep Learning

Abstract

In the context of deep learning, this article presents an original deep network, namely CentralNet, for the fusion of information coming from different sensors. This approach is designed to efficiently and automatically balance the trade-off between early and late fusion (i.e. between the fusion of low-level vs high-level information). More specifically, at each level of abstraction-the different levels of deep networks-uni-modal representations of the data are fed to a central neural network which combines them into a common embedding. In addition, a multi-objective regularization is also introduced, helping to both optimize the central network and the unimodal networks. Experiments on four multimodal datasets not only show state-of-the-art performance, but also demonstrate that CentralNet can actually choose the best possible fusion strategy for a given problem.
Fichier principal
Vignette du fichier
centralNet-journal.pdf (458.21 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01910858 , version 1 (02-11-2018)

Identifiers

Cite

Valentin Vielzeuf, Alexis Lechervy, Stéphane Pateux, Frédéric Jurie. Multi-Level Sensor Fusion with Deep Learning. IEEE Sensors Letters, 2018, 3 (1). ⟨hal-01910858⟩
384 View
1247 Download

Altmetric

Share

Gmail Facebook X LinkedIn More