Applicability of scaling laws to vision encoding models

TL;DR

This study explores how increasing sample size and model complexity improves the accuracy of vision encoding models predicting brain activity, confirming the applicability of scaling laws in this domain.

Contribution

It demonstrates that both larger training datasets and bigger models follow scaling laws, enhancing brain activity prediction accuracy in vision models.

Findings

Prediction accuracy improves with larger sample sizes.

Prediction accuracy increases with larger model parameters.

Scaling laws apply to vision encoding models.

Abstract

In this paper, we investigated how to build a high-performance vision encoding model to predict brain activity as part of our participation in the Algonauts Project 2023 Challenge. The challenge provided brain activity recorded by functional MRI (fMRI) while participants viewed images. Several vision models with parameter sizes ranging from 86M to 4.3B were used to build predictive models. To build highly accurate models, we focused our analysis on two main aspects: (1) How does the sample size of the fMRI training set change the prediction accuracy? (2) How does the prediction accuracy across the visual cortex vary with the parameter size of the vision models? The results show that as the sample size used during training increases, the prediction accuracy improves according to the scaling law. Similarly, we found that as the parameter size of the vision models increases, the prediction accuracy improves according to the scaling law. These results suggest that increasing the sample size of the fMRI training set and the parameter size of visual models may contribute to more accurate visual models of the brain and lead to a better understanding of visual neuroscience.