When Neural Networks Using Different Sensors Create Similar Features - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

When Neural Networks Using Different Sensors Create Similar Features

Abstract

Multimodal problems are omnipresent in the real world: autonomous driving, robotic grasping, scene understanding, etc... We draw from the well-developed analysis of similarity to provide an example of a problem where neural networks are trained from different sensors, and where the features extracted from these sensors still carry similar information. More precisely, we demonstrate that for each sensor, the linear combination of the features from the last layer that correlates the most with other sensors corresponds to the classification components of the classification layer.
Fichier principal
Vignette du fichier
main.pdf (977.26 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03412575 , version 1 (03-11-2021)

Identifiers

Cite

Hugues Moreau, Andréa Vassilev, Liming Chen. When Neural Networks Using Different Sensors Create Similar Features. EAI MobiCase 2021, Nov 2021, Online, China. ⟨hal-03412575⟩
59 View
47 Download

Altmetric

Share

Gmail Facebook X LinkedIn More