FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers
- URL: http://arxiv.org/abs/2501.16297v1
- Date: Mon, 27 Jan 2025 18:36:10 GMT
- Title: FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers
- Authors: Renshan Zhang, Rui Shao, Gongwei Chen, Kaiwen Zhou, Weili Guan, Liqiang Nie,
- Abstract summary: High-resolution visual input equips multimodal large language models (MLLMs) with enhanced visual perception capabilities for real-world tasks.
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.
FALCON introduces a novel visual register technique to simultaneously eliminate redundant tokens at the stage of visual encoding.
FALCON demonstrates superior performance with a remarkable 9-fold and 16-fold reduction in visual tokens.
- Score: 59.325141146786805
- License:
- Abstract: 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 and 16-fold reduction in visual tokens.
Related papers
- Efficient Multi-modal Large Language Models via Visual Token Grouping [55.482198808206284]
High-resolution images and videos pose a barrier to their broader adoption.
compressing vision tokens in MLLMs has emerged as a promising approach to reduce inference costs.
We introduce VisToG, a novel grouping mechanism that leverages the capabilities of pre-trained vision encoders to group similar image segments.
arXiv Detail & Related papers (2024-11-26T09:36:02Z) - FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression [45.37530855889661]
High-resolution images lead to a quadratic increase in the number of visual tokens input into Multi-modal Large Language Models.
Current work develop visual token compression methods to achieve efficiency improvements, often at the expense of performance.
We build a coarse-to-fine visual token compression method, with a vision-guided sampler for compressing redundant regions with low information density, and a text-guided sampler for selecting visual tokens that are strongly correlated with the user instructions.
arXiv Detail & Related papers (2024-11-21T15:37:52Z) - Improving Multi-modal Large Language Model through Boosting Vision Capabilities [54.344077285545005]
We focus on improving the visual understanding capability for boosting the vision-language models.
We propose textbfArcana, a multiModal language model, which introduces two crucial techniques.
arXiv Detail & Related papers (2024-10-17T16:36:38Z) - Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models [15.029014337718849]
Large vision-language models (LVLMs) integrate visual information into large language models, showcasing remarkable multi-modal conversational capabilities.
In general, LVLMs rely on vision encoders to transform images into visual tokens, which are crucial for the language models to perceive image contents effectively.
We propose a non-targeted attack method referred to as VT-Attack, which constructs adversarial examples from multiple perspectives.
arXiv Detail & Related papers (2024-10-09T09:06:56Z) - ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models [77.59651787115546]
High-resolution Large Multimodal Models (LMMs) encounter the challenges of excessive visual tokens and quadratic visual complexity.
We propose ConvLLaVA, which employs ConvNeXt, a hierarchical backbone, as the visual encoder of LMM.
ConvLLaVA compresses high-resolution images into information-rich visual features, effectively preventing the generation of excessive visual tokens.
arXiv Detail & Related papers (2024-05-24T17:34:15Z) - BRAVE: Broadening the visual encoding of vision-language models [48.41146184575914]
Vision-language models (VLMs) are composed of a vision encoder, e.g. CLIP, and a language model (LM) that interprets the encoded features to solve downstream tasks.
Despite remarkable progress, VLMs are subject to several shortcomings due to the limited capabilities of vision encoders.
We introduce BRAVE, which consolidates features from multiple frozen encoders into a more versatile representation that can be directly fed as the input to a frozen LM.
arXiv Detail & Related papers (2024-04-10T17:59:45Z) - LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models [35.88374542519597]
Large Multimodal Models (LMMs) have shown significant visual reasoning capabilities by connecting a visual encoder and a large language model.
Recent LMMs incorporate more complex visual inputs, such as high-resolution images and videos, which further increases the number of visual tokens significantly.
We propose PruMerge, a novel adaptive visual token reduction strategy that significantly reduces the number of visual tokens without compromising the performance of LMMs.
arXiv Detail & Related papers (2024-03-22T17:59:52Z) - Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models [81.71651422951074]
Chain-of-Spot (CoS) method is a novel approach that enhances feature extraction by focusing on key regions of interest.
This technique allows LVLMs to access more detailed visual information without altering the original image resolution.
Our empirical findings demonstrate a significant improvement in LVLMs' ability to understand and reason about visual content.
arXiv Detail & Related papers (2024-03-19T17:59:52Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.