Zero-shot counting with a dual-stream neural network model
Abstract
Deep neural networks have provided a computational framework for understanding object recognition, grounded in the neurophysiology of the primate ventral stream, but fail to account for how we process relational aspects of a scene. For example, deep neural networks fail at problems that involve enumerating the number of elements in an array, a problem that in humans relies on parietal cortex. Here, we build a 'dual-stream' neural network model which, equipped with both dorsal and ventral streams, can generalise its counting ability to wholly novel items ('zero-shot' counting). In doing so, it forms spatial response fields and lognormal number codes that resemble those observed in macaque posterior parietal cortex. We use the dual-stream network to make successful predictions about behavioural studies of the human gaze during similar counting tasks.
Keywords
Cite
@article{arxiv.2405.09953,
title = {Zero-shot counting with a dual-stream neural network model},
author = {Jessica A. F. Thompson and Hannah Sheahan and Tsvetomira Dumbalska and Julian Sandbrink and Manuela Piazza and Christopher Summerfield},
journal= {arXiv preprint arXiv:2405.09953},
year = {2024}
}