Beyond Intermediate States: Explaining Visual Redundancy through Language

• URL: http://arxiv.org/abs/2503.20540v1
• Date: Wed, 26 Mar 2025 13:38:10 GMT
• Title: Beyond Intermediate States: Explaining Visual Redundancy through Language
• Authors: Dingchen Yang, Bowen Cao, Anran Zhang, Weibo Gu, Winston Hu, Guang Chen,
• Abstract summary: Multi-modal Large Langue Models (MLLMs) often process thousands of visual tokens.<n>Visual tokens with low ViT-[cls] association and low text-to-image attention scores can contain recognizable information.<n>We develop a more reliable method for identifying and pruning redundant visual tokens.
• Score: 7.275188652473603
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-modal Large Langue Models (MLLMs) often process thousands of visual tokens, which consume a significant portion of the context window and impose a substantial computational burden. Prior work has empirically explored visual token pruning methods based on MLLMs' intermediate states (e.g., attention scores). However, they have limitations in precisely defining visual redundancy due to their inability to capture the influence of visual tokens on MLLMs' visual understanding (i.e., the predicted probabilities for textual token candidates). To address this issue, we manipulate the visual input and investigate variations in the textual output from both token-centric and context-centric perspectives, achieving intuitive and comprehensive analysis. Experimental results reveal that visual tokens with low ViT-[cls] association and low text-to-image attention scores can contain recognizable information and significantly contribute to images' overall information. To develop a more reliable method for identifying and pruning redundant visual tokens, we integrate these two perspectives and introduce a context-independent condition to identify redundant prototypes from training images, which probes the redundancy of each visual token during inference. Extensive experiments on single-image, multi-image and video comprehension tasks demonstrate the effectiveness of our method, notably achieving 90% to 110% of the performance while pruning 80% to 90% of visual tokens.

Related papers

• Exploring Multimodal Prompt for Visualization Authoring with Large Language Models [12.43647167483504]
  We study how large language models (LLMs) interpret ambiguous or incomplete text prompts in the context of visualization authoring. We introduce visual prompts as a complementary input modality to text prompts, which help clarify user intent. We design VisPilot, which enables users to easily create visualizations using multimodal prompts, including text, sketches, and direct manipulations.
  arXiv  Detail & Related papers  (2025-04-18T14:00:55Z)
• 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.<n>How MLLMs process and utilize visual information remains unclear.<n>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)
• Introducing Visual Perception Token into Multimodal Large Language Model [53.82301522384719]
  Multimodal Large Language Model (MLLM) relies on the perception process of its vision encoder.<n>MLLM still lacks the autonomous capability to control its own visual perception processes.<n>We propose the concept of Visual Perception Token, aiming to empower MLLM with a mechanism to control its visual perception processes.
  arXiv  Detail & Related papers  (2025-02-24T18:56:12Z)
• PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model [0.0]
  hallucinations often arise from the progressive weakening of attention weight to visual tokens.<n>textbfPAINT (textbfPaying textbfAttention to textbfINformed textbfTokens) is a plug-and-play framework that intervenes in the self-attention mechanism of the Large Vision Language Models.
  arXiv  Detail & Related papers  (2025-01-21T15:22:31Z)
• [CLS] Token Tells Everything Needed for Training-free Efficient MLLMs [66.5266435598799]
  Multi-language Large Language Models (MLLMs) have recently demonstrated strong performance across a wide range of vision tasks. However, their efficient deployment remains a substantial challenge due to high computational costs and memory requirements. We introduce a simple yet effective method for train-free visual compression, called VTC- compression.
  arXiv  Detail & Related papers  (2024-12-08T05:29:39Z)
• Towards Interpreting Visual Information Processing in Vision-Language Models [24.51408101801313]
  Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images. We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM.
  arXiv  Detail & Related papers  (2024-10-09T17:55:02Z)
• Towards Semantic Equivalence of Tokenization in Multimodal LLM [149.11720372278273]
  Vision tokenization is essential for semantic alignment between vision and language.<n>This paper proposes a novel dynamic Semantic-Equivalent Vision Tokenizer (SeTok)<n>SeTok groups visual features into semantic units via a dynamic clustering algorithm.<n>The resulting vision tokens effectively preserve semantic integrity and capture both low-frequency and high-frequency visual features.
  arXiv  Detail & Related papers  (2024-06-07T17:55:43Z)
• Visual Analytics for Efficient Image Exploration and User-Guided Image Captioning [35.47078178526536]
  Recent advancements in pre-trained large-scale language-image models have ushered in a new era of visual comprehension. This paper tackles two well-known issues within the realm of visual analytics: (1) the efficient exploration of large-scale image datasets and identification of potential data biases within them; (2) the evaluation of image captions and steering of their generation process.
  arXiv  Detail & Related papers  (2023-11-02T06:21:35Z)
• Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens [76.40196364163663]
  We propose a learning-based vision-language pre-training approach, such as CLIP. We show that our method can learn more comprehensive representations and capture meaningful cross-modal correspondence.
  arXiv  Detail & Related papers  (2023-03-27T00:58:39Z)
• Visually-augmented pretrained language models for NLP tasks without images [77.74849855049523]
  Existing solutions often rely on explicit images for visual knowledge augmentation. We propose a novel textbfVisually-textbfAugmented fine-tuning approach. Our approach can consistently improve the performance of BERT, RoBERTa, BART, and T5 at different scales.
  arXiv  Detail & Related papers  (2022-12-15T16:13:25Z)
• Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting [69.77701325270047]
  This paper presents a weakly supervised pre-training method that can acquire effective scene text representations. Our network consists of an image encoder and a character-aware text encoder that extract visual and textual features. Experiments show that our pre-trained model improves F-score by +2.5% and +4.8% while transferring its weights to other text detection and spotting networks.
  arXiv  Detail & Related papers  (2022-03-08T08:10:45Z)
• Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision [57.031588264841]
  We leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps. A simple dual-encoder architecture learns to align visual and language representations of the image and text pairs using a contrastive loss. We show that the scale of our corpus can make up for its noise and leads to state-of-the-art representations even with such a simple learning scheme.
  arXiv  Detail & Related papers  (2021-02-11T10:08:12Z)

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.