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

arXiv:2302.08913v4 Announce Type: replace-cross
Abstract: 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 \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 …

abstract agents architectures arxiv autonomous autonomous agents cars communication communities cs.ai cs.cv cs.lg driving embedded image networks neural networks processing question robots self-driving systems training type visual world