Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy

• URL: http://arxiv.org/abs/2411.15453v1
• Date: Sat, 23 Nov 2024 05:03:32 GMT
• Title: Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy
• Authors: Te Yang, Jian Jia, Xiangyu Zhu, Weisong Zhao, Bo Wang, Yanhua Cheng, Yan Li, Shengyuan Liu, Quan Chen, Peng Jiang, Kun Gai, Zhen Lei,
• Abstract summary: There is a significant gap in instruction-following capabilities between Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) We propose Visual-Modality Token Compression (VMTC) and Cross-Modality Attention Inhibition (CMAI) strategies to alleviate this gap.
• Score: 37.471419716572086
• License:
• Abstract: Large Language Models (LLMs) have strong instruction-following capability to interpret and execute tasks as directed by human commands. Multimodal Large Language Models (MLLMs) have inferior instruction-following ability compared to LLMs. However, there is a significant gap in the instruction-following capabilities between the MLLMs and LLMs. In this study, we conduct a pilot experiment, which demonstrates that spatially down-sampling visual tokens significantly enhances the instruction-following capability of MLLMs. This is attributed to the substantial redundancy in visual modality. However, this intuitive method severely impairs the MLLM's multimodal understanding capability. In this paper, we propose Visual-Modality Token Compression (VMTC) and Cross-Modality Attention Inhibition (CMAI) strategies to alleviate this gap between MLLMs and LLMs by inhibiting the influence of irrelevant visual tokens during content generation, increasing the instruction-following ability of the MLLMs while retaining their multimodal understanding capacity. In VMTC module, the primary tokens are retained and the redundant tokens are condensed by token clustering and merging. In CMAI process, we aggregate text-to-image attentions by text-to-text attentions to obtain a text-to-image focus score. Attention inhibition is performed on the text-image token pairs with low scores. Our comprehensive experiments over instruction-following capabilities and VQA-V2, GQA, TextVQA, MME and MMBench five benchmarks, demonstrate that proposed strategy significantly enhances the instruction following capability of MLLMs while preserving the ability to understand and process multimodal inputs.

Related papers

• Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding [41.43688559565315]
  We present a novel OCR-free document understanding framework based on pretrained Multimodal Large Language Models (MLLMs) Our approach employs multi-scale visual features to handle various font sizes within document images. We introduce a novel instruction tuning task, which facilitates the model's text-reading capability by learning to predict the relative positions of input text.
  arXiv  Detail & Related papers  (2024-11-08T00:58:12Z)
• LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation [60.02145113467427]
  This work introduces a fine-tuning approach that integrates large language models with the pretrained CLIP visual encoder. To address the challenge of LLMs' autoregressive nature, we propose a caption-to-caption contrastive learning framework. Our method achieves substantial performance gains on various downstream tasks.
  arXiv  Detail & Related papers  (2024-11-07T18:59:16Z)
• Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See [37.7015406019386]
  Multimodal Large Language Models (MLLMs) treat visual tokens from visual encoders as text tokens. As token counts grow, the quadratic scaling of computation in LLMs introduces an efficiency bottleneck. In this study, we investigate the redundancy in visual computation at both the parameter and computational pattern levels within LLaVA.
  arXiv  Detail & Related papers  (2024-10-08T16:13:24Z)
• SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs [40.74693126923826]
  Multimodal Large Language Models (MLLMs) have recently demonstrated remarkable perceptual and reasoning abilities. Training adapters with image-level supervision often results in significant misalignment. We introduce Supervised Embedding Alignment (SEA), a token-level alignment method that leverages vision-language pre-trained models.
  arXiv  Detail & Related papers  (2024-08-21T17:58:02Z)
• ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models [73.34709921061928]
  We propose a training-free method to inject visual referring into Multimodal Large Language Models (MLLMs) We observe the relationship between text prompt tokens and visual tokens in MLLMs, where attention layers model the connection between them. We optimize a learnable visual token based on an energy function, enhancing the strength of referential regions in the attention map.
  arXiv  Detail & Related papers  (2024-07-31T11:40:29Z)
• Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge [76.45868419402265]
  multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs. This paper proposes a new visual prompt approach to integrate fine-grained external knowledge, gleaned from specialized vision models, into MLLMs.
  arXiv  Detail & Related papers  (2024-07-05T17:43:30Z)
• Towards Semantic Equivalence of Tokenization in Multimodal LLM [149.11720372278273]
  Vision tokenization is essential for semantic alignment between vision and language. This paper proposes a novel dynamic Semantic-Equivalent Vision Tokenizer (SeTok) SeTok groups visual features into semantic units via a dynamic clustering algorithm. 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)
• Prompt Highlighter: Interactive Control for Multi-Modal LLMs [50.830448437285355]
  This study targets a critical aspect of multi-modal LLMs' (LLMs&VLMs) inference: explicit controllable text generation. We introduce a novel inference method, Prompt Highlighter, which enables users to highlight specific prompt spans to interactively control the focus during generation. We find that, during inference, guiding the models with highlighted tokens through the attention weights leads to more desired outputs.
  arXiv  Detail & Related papers  (2023-12-07T13:53:29Z)
• LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge [58.82222646803248]
  Multimodal Large Language Models (MLLMs) have endowed LLMs with the ability to perceive and understand multi-modal signals. Most of the existing MLLMs mainly adopt vision encoders pretrained on coarsely aligned image-text pairs, leading to insufficient extraction and reasoning of visual knowledge. We propose a dual-Level vIsual knedgeOwl eNhanced Multimodal Large Language Model (LION), which empowers the MLLM by injecting visual knowledge in two levels.
  arXiv  Detail & Related papers  (2023-11-20T15:56:44Z)
• Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics [32.123919380959485]
  Multi-modal large language models (MLLMs) are trained based on large language models (LLM) While they excel in multi-modal tasks, the pure NLP abilities of MLLMs are often underestimated and left untested. We show that visual instruction tuning, a prevailing strategy for transitioning LLMs into MLLMs, unexpectedly and interestingly helps models attain both improved truthfulness and ethical alignment.
  arXiv  Detail & Related papers  (2023-09-13T17:57:21Z)

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.