Aligned with LLM: a new multi-modal training paradigm for encoding fMRI activity in visual cortex

TL;DR

This paper introduces a novel multi-modal training paradigm aligned with large language models to improve the encoding of fMRI activity in the visual cortex, leveraging text-image alignment for enhanced brain activity prediction.

Contribution

The paper proposes a new multi-modal training approach aligned with LLMs, specifically using text-image alignment to improve visual cortex encoding models.

Findings

Enhanced performance of the visual encoding model with the new paradigm

Effective use of LLM-generated descriptions and contrast loss for alignment

Significant improvement in fMRI activity prediction accuracy

Abstract

Recently, there has been a surge in the popularity of pre trained large language models (LLMs) (such as GPT-4), sweeping across the entire Natural Language Processing (NLP) and Computer Vision (CV) communities. These LLMs have demonstrated advanced multi-modal understanding capabilities and showcased strong performance across various benchmarks. The LLM has started to embody traits of artificial general intelligence, which holds vital guidance for enhancing brain-like characteristics within visual encoding models. Hence, This paper proposes a new multi-modal training paradigm, aligning with LLM, for encoding fMRI activity in visual cortex. Based on this paradigm, we trained an encoding model in fMRI data named the LLM-Visual Encoding Model (LLM-VEM). Specifically, we utilize LLM (miniGPT4) to generate descriptive text for all stimulus images, forming a high-quality textual description set. Moreover, we use the pre-trained text encoder (CLIP) to process these detailed descriptions, obtaining the text embedding features. Next, we use the contrast loss function to minimize the distance between the image embedding features and the text embedding features to complete the alignment operation of the stimulus image and text information. With the assistance of the pre-trained LLM, this alignment process facilitates better learning of the visual encoding model, resulting in higher precision. The final experimental results indicate that our training paradigm has significantly aided in enhancing the performance of the visual encoding model.