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

1 code implementation • 4 Feb 2023 • Matéo Mahaut, Francesca Franzon, Roberto Dessì, Marco Baroni

As a first step in this direction, we systematically explore the task of \textit{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.

Self-Driving Cars