Skip to yearly menu bar Skip to main content


Poster

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

Kamal Gupta · Gowthami Somepalli · Anubhav Anubhav · Vinoj Yasanga Jayasundara Magalle Hewa · Matthias Zwicker · Abhinav Shrivastava

Keywords: [ Machine Learning ] [ Self-Supervised Learning ] [ Transformers ]


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).

Chat is not available.