通过轻量剪枝保留关键文本区域，显著降低文档理解的计算开销。
Index-Preserving Lightweight Token Pruning for Efficient Document Understanding in Vision-Language Models
- 用二值分类器剔除图像中非文本区域，减少冗余信息
- 通过最大池化修复断裂文本区域，保持空间连贯性
- 在真实文档数据集上实现高精度与低计算成本的平衡
视觉语言模型（VLMs）在文档理解任务中取得显著进展，但其高计算需求仍是主要挑战。为缓解计算负担，我们提出一种轻量级标记剪枝框架，在VLM处理前过滤文档图像中的非信息背景区域。该方法采用二值块级分类器移除非文本区域，并通过最大池化精炼步骤恢复断裂的文本区域，提升空间连贯性。在真实文档数据集上的实验表明，该方法显著降低计算成本，同时保持相近的准确率。
原文摘要 · Abstract (English)
Recent progress in vision-language models (VLMs) has led to impressive results in document understanding tasks, but their high computational demands remain a challenge. To mitigate the compute burdens, we propose a lightweight token pruning framework that filters out non-informative background regions from document images prior to VLM processing. A binary patch-level classifier removes non-text areas, and a max-pooling refinement step recovers fragmented text regions to enhance spatial coherence. Experiments on real-world document datasets demonstrate that our approach substantially lowers computational costs, while maintaining comparable accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。