DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming
- URL: http://arxiv.org/abs/2406.19101v2
- Date: Tue, 3 Sep 2024 03:51:37 GMT
- Title: DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming
- Authors: Jiaxin Zhang, Wentao Yang, Songxuan Lai, Zecheng Xie, Lianwen Jin,
- Abstract summary: DocKylin is a document-centric MLLM that performs visual content slimming at both the pixel and token levels.
We introduce an Adaptive Pixel Slimming (APS) preprocessing module to perform pixel-level slimming.
We also propose a novel Dynamic Token Slimming (DTS) module to conduct token-level slimming.
- Score: 33.40963475653868
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Current multimodal large language models (MLLMs) face significant challenges in visual document understanding (VDU) tasks due to the high resolution, dense text, and complex layouts typical of document images. These characteristics demand a high level of detail perception ability from MLLMs. While increasing input resolution improves detail perception capability, it also leads to longer sequences of visual tokens, increasing computational costs and straining the models' ability to handle long contexts. To address these challenges, we introduce DocKylin, a document-centric MLLM that performs visual content slimming at both the pixel and token levels, thereby reducing token sequence length in VDU scenarios. We introduce an Adaptive Pixel Slimming (APS) preprocessing module to perform pixel-level slimming, increasing the proportion of informative pixels. Moreover, we propose a novel Dynamic Token Slimming (DTS) module to conduct token-level slimming, filtering essential tokens and removing others to adaptively create a more compact visual sequence. Experiments demonstrate DocKylin's promising performance across various VDU benchmarks and the effectiveness of each component.
Related papers
- PerspectiveNet: Multi-View Perception for Dynamic Scene Understanding [1.2781698000674653]
PerspectiveNet is a lightweight model for generating long descriptions across multiple camera views.
Our approach utilizes a vision encoder, a compact connector module, and large language models.
The resulting model is lightweight, ensuring efficient training and inference, while remaining highly effective.
arXiv Detail & Related papers (2024-10-22T08:57:17Z) - AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding [96.01726275876548]
We present AdaptVision, a multimodal large language model specifically designed to dynamically process input images at varying resolutions.
We devise a dynamic image partitioning module that adjusts the number of visual tokens according to the size and aspect ratio of images.
Our model is capable of processing images with resolutions up to $1008times 1008$.
arXiv Detail & Related papers (2024-08-30T03:16:49Z) - Instruction Tuning-free Visual Token Complement for Multimodal LLMs [51.138806401996696]
multimodal large language models (MLLMs) have promised an elegant bridge between vision and language.
We propose a Visual Token Complement framework (VTC) that helps MLLMs regain the missing visual features.
Our VTC integrates text-to-image generation as a guide to identifying the text-irrelevant features, and a visual selector is then developed to generate complementary visual tokens.
arXiv Detail & Related papers (2024-08-09T12:13:01Z) - LVLM-empowered Multi-modal Representation Learning for Visual Place Recognition [17.388776062997813]
We try to build a discriminative global representations by fusing image data and text descriptions of the the visual scene.
The motivation is twofold: (1) Current Large Vision-Language Models (LVLMs) demonstrate extraordinary emergent capability in visual instruction following, and thus provide an efficient and flexible manner in generating text descriptions of images.
Although promising, leveraging LVLMs to build multi-modal VPR solutions remains challenging in efficient multi-modal fusion.
arXiv Detail & Related papers (2024-07-09T10:15:31Z) - From Text to Pixel: Advancing Long-Context Understanding in MLLMs [70.78454154014989]
We introduce SEEKER, a multimodal large language model designed to tackle this issue.
SEEKER aims to optimize the compact encoding of long text by compressing the text sequence into the visual pixel space via images.
Our experiments on six long-context multimodal tasks demonstrate that SEEKER can leverage fewer image tokens to convey the same amount of textual information compared with the OCR-based approach.
arXiv Detail & Related papers (2024-05-23T06:17:23Z) - HRVDA: High-Resolution Visual Document Assistant [32.51417315241559]
We propose a High-Resolution Visual Document Assistant (HRVDA) to bridge the gap between MLLMs and visual document understanding.
HRVDA employs a content filtering mechanism and an instruction filtering module to filter out the content-agnostic visual tokens and instruction-agnostic visual tokens.
Our model achieves state-of-the-art performance across multiple document understanding datasets.
arXiv Detail & Related papers (2024-04-10T11:10:50Z) - Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want [58.091825321168514]
We introduce the Draw-and-Understand project: a new model, a multi-domain dataset, and a challenging benchmark for visual prompting.
Specifically, we propose a new end-to-end trained Multimodal Large Language Model (MLLM) that connects a vision encoder, a visual prompt encoder and an LLM.
To advance visual prompting research for MLLMs, we introduce MDVP-Data and MDVP-Bench.
arXiv Detail & Related papers (2024-03-29T16:26:20Z) - 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) - Enhancing Visual Document Understanding with Contrastive Learning in
Large Visual-Language Models [56.76307866160105]
We propose a contrastive learning framework, termed Document Object COntrastive learning (DoCo)
DoCo leverages an auxiliary multimodal encoder to obtain the features of document objects and align them to the visual features generated by the vision encoder of Large Visual-Language Models (LVLMs)
We demonstrate that the proposed DoCo serves as a plug-and-play pre-training method, which can be employed in the pre-training of various LVLMs without inducing any increase in computational complexity during the inference process.
arXiv Detail & Related papers (2024-02-29T10:17:27Z)
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.