Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model

TL;DR

This paper introduces AcFormer, a novel vision-language connector for multimodal large language models that leverages visual anchors to improve accuracy and reduce computational costs significantly.

Contribution

The study proposes a new vision-language connector called AcFormer that uses visual anchors from Vision Transformers to enhance multimodal model performance efficiently.

Findings

Reduces computational costs by nearly two-thirds.

Outperforms baseline methods in accuracy.

Effectively leverages visual anchors for information aggregation.

Abstract

In the realm of Multimodal Large Language Models (MLLMs), vision-language connector plays a crucial role to link the pre-trained vision encoders with Large Language Models (LLMs). Despite its importance, the vision-language connector has been relatively less explored. In this study, we aim to propose a strong vision-language connector that enables MLLMs to achieve high accuracy while maintain low computation cost. We first reveal the existence of the visual anchors in Vision Transformer and propose a cost-effective search algorithm to extract them. Building on these findings, we introduce the Anchor Former (AcFormer), a novel vision-language connector designed to leverage the rich prior knowledge obtained from these visual anchors during pretraining, guiding the aggregation of information. Through extensive experimentation, we demonstrate that the proposed method significantly reduces computational costs by nearly two-thirds compared with baseline, while simultaneously outperforming baseline methods. This highlights the effectiveness and efficiency of AcFormer. Codes are available at https://github.com/liuhaogeng/Anchor-Former.