Perceptual Grouping and Adaptive Tokenisation

Presented by Marius Aasan, Postdoctoral Research Fellow at SFI Visual Intelligence

Abstract

As vision modelling is pivoting towards transformer based models, the role of tokenization — the way models partition and interpret the data — becomes increasingly important, as it is the central interface between analysis and data, that dictates how AI models synthesise semantic understanding from sensory data. This talk discusses how this interfact can be leveraged for better interpretability, incorporation of prior knowledge, and new opportunities in self-supervised learning signals. We also discuss the challenges involved in how these mechanisms currently work, and what interesting research opportunities that can be derived from tokenization in the broader context of modern representation learning.