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

2024/05/16 by Jessica A. F. Thompson, Hannah Sheahan, Thompson, Jessica A. F. +9 · 3 citations
Environmental Science · Computer Science · Mathematics · #Air Quality Monitoring and Forecasting #Gaussian Processes and Bayesian Inference #Statistical Methods and Inference

paper · pdf · doi:10.48550/arxiv.2405.09953

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.

Cited by

• A Rate-Distortion Perspective on the Emergence of Number Sense in Unsupervised Generative Models
• A Deep Learning Model of Mental Rotation Informed by Interactive VR Experiments
• Sequential Enumeration in Large Language Models

Related

• The Quest for an Integrated Set of Neural Mechanisms Underlying Object Recognition in Primates
• A Dual-Stream Neural Network Explains the Functional Segregation of Dorsal and Ventral Visual Pathways in Human Brains
• Brain-Like Object Recognition with High-Performing Shallow Recurrent\n ANNs
• STSBench: A Large-Scale Dataset for Modeling Neuronal Activity in the Dorsal Stream of Primate Visual Cortex
• Evaluating Visual Number Discrimination in Deep Neural Networks