PatchGame: Learning to Signal Mid-level Patches in Referential Games

Kamal Gupta, Gowthami Somepalli, Anubhav Gupta, Vinoj Jayasundara, Matthias Zwicker, Abhinav Shrivastava

Keywords: emergent language, referential games, self-supervised learning, mid-level patches

Abstract: We study a referential game (a type of signaling game) where two agents communicate with each other via a discrete bottleneck to achieve a common goal. In our referential game, the goal of the speaker is to compose a message or a symbolic representation of "important" image patches, while the task for the listener is to match the speaker's message to a different view of the same image. We show that it is indeed possible for the two agents to develop a communication protocol without explicit or implicit supervision. We further investigate the developed protocol and show the applications in speeding up recent Vision Transformers by using only important patches, and as pre-training for downstream recognition tasks (e.g., classification).

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

TL;DR: Emergent communication via mid-level patches in a referential game played on a large-scale image dataset

Code: https://github.com/kampta/PatchGame

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2111.01785/code)