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.<n>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.<n>FALCON introduces a novel visual register technique to simultaneously eliminate redundant tokens at the stage of visual encoding.<n>FALCON demonstrates superior performance with a remarkable 9-fold and 16-fold reduction in visual tokens.
• Score: 59.325141146786805
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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

• METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models [92.37117312251755]
  We propose a progressive pruning framework, namely Multi-Encoder collaboraTivE tOken pRuning (METEOR)<n>For multi-vision encoding, we discard redundant tokens within each encoder via a rank guided collaborative token assignment strategy.<n>For multi-vision fusion, we combine the visual features from different encoders while reducing cross-encoder redundancy with cooperative pruning.
  arXiv  Detail & Related papers  (2025-07-28T13:50:53Z)
• Rethinking Visual Token Reduction in LVLMs under Cross-modal Misalignment [38.04426918886084]
  Vision-Language Models (LVLMs) encode visual inputs as dense sequences of patch-level tokens to capture fine-grained semantics.<n>Previous efforts have explored visual token reduction either prior to or within the large language models (LLMs)<n>We introduce VisionDrop, a training-free, visual-only pruning framework that selects informative visual tokens based on intra-modal (visual-to-visual) attention.
  arXiv  Detail & Related papers  (2025-06-27T14:55:40Z)
• Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models [18.02840698188587]
  We propose a novel kernel-based method to align CLIP's visual representation with that of DINOv2.<n>Our image-only alignment fine-tuning exhibits significant improvements in zero-shot object recognition, fine-grained spatial reasoning.
  arXiv  Detail & Related papers  (2025-06-03T07:44:43Z)
• DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs [124.52164183968145]
  We present DyMU, an efficient, training-free framework that reduces the computational burden of vision-language models (VLMs) Our approach comprises two key components. First, Dynamic Token Merging (DToMe) reduces the number of visual token embeddings by merging similar tokens based on image complexity. Second, Virtual Token Unmerging (VTU) simulates the expected token sequence for large language models (LLMs) by efficiently reconstructing the attention dynamics of a full sequence.
  arXiv  Detail & Related papers  (2025-04-23T18:38:18Z)
• Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference [28.24397677839652]
  Multimodal large language models (MLLMs) improve performance on vision-language tasks by integrating visual features from pre-trained vision encoders into large language models. How MLLMs process and utilize visual information remains unclear. We propose Hierarchical Modality-Aware Pruning (HiMAP), a plug-and-play inference acceleration method that dynamically prunes image tokens at specific layers, reducing computational costs by approximately 65% without sacrificing performance.
  arXiv  Detail & Related papers  (2025-03-17T12:31:23Z)
• Efficient Multi-modal Large Language Models via Visual Token Grouping [55.482198808206284]
  High-resolution images and videos pose a barrier to their broader adoption.<n> compressing vision tokens in MLLMs has emerged as a promising approach to reduce inference costs.<n>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)
• 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.