Referential communication in heterogeneous communities of pre-trained visual deep networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mahaut, Matéo, Franzon, Francesca, Dessì, Roberto, Baroni, Marco
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910905801900032
author Mahaut, Matéo
Franzon, Francesca
Dessì, Roberto
Baroni, Marco
author_facet Mahaut, Matéo
Franzon, Francesca
Dessì, Roberto
Baroni, Marco
contents As large pre-trained image-processing neural networks are being embedded in autonomous agents such as self-driving cars or robots, the question arises of how such systems can communicate with each other about the surrounding world, despite their different architectures and training regimes. As a first step in this direction, we systematically explore the task of referential communication in a community of heterogeneous state-of-the-art pre-trained visual networks, showing that they can develop, in a self-supervised way, a shared protocol to refer to a target object among a set of candidates. This shared protocol can also be used, to some extent, to communicate about previously unseen object categories of different granularity. Moreover, a visual network that was not initially part of an existing community can learn the community's protocol with remarkable ease. Finally, we study, both qualitatively and quantitatively, the properties of the emergent protocol, providing some evidence that it is capturing high-level semantic features of objects.
format Preprint
id arxiv_https___arxiv_org_abs_2302_08913
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Referential communication in heterogeneous communities of pre-trained visual deep networks
Mahaut, Matéo
Franzon, Francesca
Dessì, Roberto
Baroni, Marco
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
As large pre-trained image-processing neural networks are being embedded in autonomous agents such as self-driving cars or robots, the question arises of how such systems can communicate with each other about the surrounding world, despite their different architectures and training regimes. As a first step in this direction, we systematically explore the task of referential communication in a community of heterogeneous state-of-the-art pre-trained visual networks, showing that they can develop, in a self-supervised way, a shared protocol to refer to a target object among a set of candidates. This shared protocol can also be used, to some extent, to communicate about previously unseen object categories of different granularity. Moreover, a visual network that was not initially part of an existing community can learn the community's protocol with remarkable ease. Finally, we study, both qualitatively and quantitatively, the properties of the emergent protocol, providing some evidence that it is capturing high-level semantic features of objects.
title Referential communication in heterogeneous communities of pre-trained visual deep networks
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2302.08913