LLaVA-Zip: Adaptive Visual Token Compression with Intrinsic Image Information

• URL: http://arxiv.org/abs/2412.08771v1
• Date: Wed, 11 Dec 2024 20:46:06 GMT
• Title: LLaVA-Zip: Adaptive Visual Token Compression with Intrinsic Image Information
• Authors: Ke Wang, Hong Xuan,
• Abstract summary: We propose Dynamic Feature Map Reduction (DFMR) based on LLaVA-1.5 to address the challenge of visual token overload. DFMR dynamically compresses the visual tokens, freeing up token capacity. Our experimental results demonstrate that integrating DFMR into LLaVA-1.5 significantly improves the performance of LLaVA in varied visual token lengths.
• Score: 4.33464415015353
• License:
• Abstract: Multi-modal large language models (MLLMs) utilizing instruction-following data, such as LLaVA, have achieved great progress in the industry. A major limitation in these models is that visual tokens consume a substantial portion of the maximum token limit in large language models (LLMs), leading to increased computational demands and decreased performance when prompts include multiple images or videos. Industry solutions often mitigate this issue by increasing computational power, but this approach is less feasible in academic environments with limited resources. In this study, we propose Dynamic Feature Map Reduction (DFMR) based on LLaVA-1.5 to address the challenge of visual token overload. DFMR dynamically compresses the visual tokens, freeing up token capacity. Our experimental results demonstrate that integrating DFMR into LLaVA-1.5 significantly improves the performance of LLaVA in varied visual token lengths, offering a promising solution for extending LLaVA to handle multi-image and video scenarios in resource-constrained academic environments and it can also be applied in industry settings for data augmentation to help mitigate the scarcity of open-domain image-text pair datasets in the continued pretraining stage.

Related papers

• Visual RAG: Expanding MLLM visual knowledge without fine-tuning [5.341192792319891]
  This paper introduces Visual RAG, that synergically combines the MLLMs capability to learn from the context, with a retrieval mechanism. In this way, the resulting system is not limited to the knowledge extracted from the training data, but can be updated rapidly and easily without fine-tuning. It greatly reduces the computational costs for improving the model image classification performance, and augments the model knowledge to new visual domains and tasks it was not trained for.
  arXiv  Detail & Related papers  (2025-01-18T17:43:05Z)
• FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance [7.889590793589825]
  We introduce FOLDER, a simple yet effective plug-and-play module designed to reduce the length of the visual token sequence. We analyze the information loss introduced by different reduction strategies and develop FOLDER to preserve key information while removing visual redundancy. FOLDER achieves comparable or even better performance than the original models, while dramatically reducing complexity by removing up to 70% of visual tokens.
  arXiv  Detail & Related papers  (2025-01-05T03:28:45Z)
• AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning [19.68349294206012]
  We propose a training-free adaptive inference method for multi-modal LLMs. With a minimalist design, our method can be applied to both video and image LLMs. Under a similar computational cost, our method outperforms the state-of-the-art methods in long video understanding.
  arXiv  Detail & Related papers  (2024-12-04T11:47:57Z)
• 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)
• LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval [14.136397687227111]
  We propose the Large Language-and-Vision Assistant for Moment Retrieval (LLaVA-MR) LLaVA-MR enables accurate moment retrieval and contextual grounding in videos using Multimodal Large Language Models (MLLMs) Evaluations on benchmarks like Charades-STA and QVHighlights demonstrate that LLaVA-MR outperforms 11 state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-11-21T09:34:23Z)
• Inference Optimal VLMs Need Only One Visual Token but Larger Models [54.01228554126122]
  Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks. VLMs are often constrained by high latency during inference due to substantial compute required to process the large number of input tokens. We take some initial steps towards building approaches tailored for high token compression settings.
  arXiv  Detail & Related papers  (2024-11-05T18:54:21Z)
• 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)
• VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation [66.00245701441547]
  We introduce a novel approach to reduce vision compute by leveraging redundant vision tokens "skipping layers" rather than decreasing the number of vision tokens. Our method, VideoLLM-MoD, is inspired by mixture-of-depths LLMs and addresses the challenge of numerous vision tokens in long-term or streaming video.
  arXiv  Detail & Related papers  (2024-08-29T17:21:58Z)
• Dense Connector for MLLMs [89.50595155217108]
  We introduce the Dense Connector - a plug-and-play vision-language connector that significantly enhances existing MLLMs. Building on this, we also propose the Efficient Dense Connector, which achieves performance comparable to LLaVA-v1.5 with only 25% of the visual tokens. Our model, trained solely on images, showcases remarkable zero-shot capabilities in video understanding as well.
  arXiv  Detail & Related papers  (2024-05-22T16:25:03Z)
• 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)
• An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models [65.37846460916042]
  We find out that the attention computation over visual tokens is of extreme inefficiency in the deep layers of popular LVLMs. We introduce FastV, a versatile plug-and-play method designed to optimize computational efficiency.
  arXiv  Detail & Related papers  (2024-03-11T14:35:32Z)

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.