FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Renshan, Shao, Rui, Chen, Gongwei, Zhang, Miao, Zhou, Kaiwen, Guan, Weili, Nie, Liqiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915364778016768
author Zhang, Renshan
Shao, Rui
Chen, Gongwei
Zhang, Miao
Zhou, Kaiwen
Guan, Weili
Nie, Liqiang
author_facet Zhang, Renshan
Shao, Rui
Chen, Gongwei
Zhang, Miao
Zhou, Kaiwen
Guan, Weili
Nie, Liqiang
contents The incorporation of high-resolution visual input equips multimodal large language models (MLLMs) with enhanced visual perception capabilities for real-world tasks. However, most existing high-resolution MLLMs rely on a cropping-based approach to process images, which leads to fragmented visual encoding and a sharp increase in redundant tokens. To tackle these issues, we propose the FALCON model. FALCON introduces a novel visual register technique to simultaneously: 1) Eliminate redundant tokens at the stage of visual encoding. To directly address the visual redundancy present in the output of vision encoder, we propose a Register-based Representation Compacting (ReCompact) mechanism. This mechanism introduces a set of learnable visual registers designed to adaptively aggregate essential information while discarding redundancy. It enables the encoder to produce a more compact visual representation with a minimal number of output tokens, thus eliminating the need for an additional compression module. 2) Ensure continuity in visual encoding. To address the potential encoding errors caused by fragmented visual inputs, we develop a Register Interactive Attention (ReAtten) module. This module facilitates effective and efficient information exchange across sub-images by enabling interactions between visual registers. It ensures the continuity of visual semantics throughout the encoding. We conduct comprehensive experiments with FALCON on high-resolution benchmarks across a wide range of scenarios. FALCON demonstrates superior performance with a remarkable 9-fold reduction in visual tokens.
format Preprint
id arxiv_https___arxiv_org_abs_2501_16297
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers
Zhang, Renshan
Shao, Rui
Chen, Gongwei
Zhang, Miao
Zhou, Kaiwen
Guan, Weili
Nie, Liqiang
Computer Vision and Pattern Recognition
The incorporation of high-resolution visual input equips multimodal large language models (MLLMs) with enhanced visual perception capabilities for real-world tasks. However, most existing high-resolution MLLMs rely on a cropping-based approach to process images, which leads to fragmented visual encoding and a sharp increase in redundant tokens. To tackle these issues, we propose the FALCON model. FALCON introduces a novel visual register technique to simultaneously: 1) Eliminate redundant tokens at the stage of visual encoding. To directly address the visual redundancy present in the output of vision encoder, we propose a Register-based Representation Compacting (ReCompact) mechanism. This mechanism introduces a set of learnable visual registers designed to adaptively aggregate essential information while discarding redundancy. It enables the encoder to produce a more compact visual representation with a minimal number of output tokens, thus eliminating the need for an additional compression module. 2) Ensure continuity in visual encoding. To address the potential encoding errors caused by fragmented visual inputs, we develop a Register Interactive Attention (ReAtten) module. This module facilitates effective and efficient information exchange across sub-images by enabling interactions between visual registers. It ensures the continuity of visual semantics throughout the encoding. We conduct comprehensive experiments with FALCON on high-resolution benchmarks across a wide range of scenarios. FALCON demonstrates superior performance with a remarkable 9-fold reduction in visual tokens.
title FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.16297