Saved in:
Bibliographic Details
Main Authors: Liang, Yuxuan, Li, Xu, Chen, Xiaolei, Chen, Haotian, Zheng, Yi, Lai, Chenghang, Li, Bin, Xue, Xiangyang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.14276
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917901553893376
author Liang, Yuxuan
Li, Xu
Chen, Xiaolei
Chen, Haotian
Zheng, Yi
Lai, Chenghang
Li, Bin
Xue, Xiangyang
author_facet Liang, Yuxuan
Li, Xu
Chen, Xiaolei
Chen, Haotian
Zheng, Yi
Lai, Chenghang
Li, Bin
Xue, Xiangyang
contents As the demand for high-resolution image processing in Large Vision-Language Models (LVLMs) grows, sub-image partitioning has become a popular approach for mitigating visual information loss associated with fixed-resolution processing. However, existing partitioning methods uniformly process sub-images, resulting in suboptimal image understanding. In this work, we reveal that the sub-images with higher semantic relevance to the entire image encapsulate richer visual information for preserving the model's visual understanding ability. Therefore, we propose the Global Semantic-guided Weight Allocator (GSWA) module, which dynamically allocates weights to sub-images based on their relative information density, emulating human visual attention mechanisms. This approach enables the model to focus on more informative regions, overcoming the limitations of uniform treatment. We integrate GSWA into the InternVL2-2B framework to create SleighVL, a lightweight yet high-performing model. Extensive experiments demonstrate that SleighVL outperforms models with comparable parameters and remains competitive with larger models. Our work provides a promising direction for more efficient and contextually aware high-resolution image processing in LVLMs, advancing multimodal system development.
format Preprint
id arxiv_https___arxiv_org_abs_2501_14276
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Global Semantic-Guided Sub-image Feature Weight Allocation in High-Resolution Large Vision-Language Models
Liang, Yuxuan
Li, Xu
Chen, Xiaolei
Chen, Haotian
Zheng, Yi
Lai, Chenghang
Li, Bin
Xue, Xiangyang
Computer Vision and Pattern Recognition
Artificial Intelligence
As the demand for high-resolution image processing in Large Vision-Language Models (LVLMs) grows, sub-image partitioning has become a popular approach for mitigating visual information loss associated with fixed-resolution processing. However, existing partitioning methods uniformly process sub-images, resulting in suboptimal image understanding. In this work, we reveal that the sub-images with higher semantic relevance to the entire image encapsulate richer visual information for preserving the model's visual understanding ability. Therefore, we propose the Global Semantic-guided Weight Allocator (GSWA) module, which dynamically allocates weights to sub-images based on their relative information density, emulating human visual attention mechanisms. This approach enables the model to focus on more informative regions, overcoming the limitations of uniform treatment. We integrate GSWA into the InternVL2-2B framework to create SleighVL, a lightweight yet high-performing model. Extensive experiments demonstrate that SleighVL outperforms models with comparable parameters and remains competitive with larger models. Our work provides a promising direction for more efficient and contextually aware high-resolution image processing in LVLMs, advancing multimodal system development.
title Global Semantic-Guided Sub-image Feature Weight Allocation in High-Resolution Large Vision-Language Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2501.14276