Zero-shot counting with a dual-stream neural network model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Thompson, Jessica A. F., Sheahan, Hannah, Dumbalska, Tsvetomira, Sandbrink, Julian, Piazza, Manuela, Summerfield, Christopher
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913352660287488
author Thompson, Jessica A. F.
Sheahan, Hannah
Dumbalska, Tsvetomira
Sandbrink, Julian
Piazza, Manuela
Summerfield, Christopher
author_facet Thompson, Jessica A. F.
Sheahan, Hannah
Dumbalska, Tsvetomira
Sandbrink, Julian
Piazza, Manuela
Summerfield, Christopher
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_09953
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Zero-shot counting with a dual-stream neural network model
Thompson, Jessica A. F.
Sheahan, Hannah
Dumbalska, Tsvetomira
Sandbrink, Julian
Piazza, Manuela
Summerfield, Christopher
Neurons and Cognition
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.
title Zero-shot counting with a dual-stream neural network model
topic Neurons and Cognition
url https://arxiv.org/abs/2405.09953